Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.
Awesome Lists | Featured Topics | Projects
https://github.com/rlczddl/awesome-3d-human-reconstruction

List: awesome-3d-human-reconstruction
Last synced: about 2 months ago
JSON representation
Host: GitHub
URL: https://github.com/rlczddl/awesome-3d-human-reconstruction
Owner: rlczddl
Created: 2020-08-23T06:20:03.000Z (about 4 years ago)
Default Branch: master
Last Pushed: 2024-01-17T01:51:01.000Z (8 months ago)
Last Synced: 2024-05-20T01:01:08.393Z (4 months ago)
Size: 146 KB
Stars: 785
Watchers: 50
Forks: 85
Open Issues: 0
Metadata Files:
- Readme: README.md
Awesome Lists containing this project

Awesome-Computer-Vision - 2
README

        # awesome 3d human reconstruction 

A curated list of related resources for 3d human reconstruction. Your contributions are welcome!

## Contents

 - [papers](#3d-human)

    - [AIGC](#AIGC)

    - [nerf pifu_3dgs](#nerf_pifu_3dgs)

    - [geo fusion](#geo_fusion)

    - [photo](#photo)

    - [3D human whole body](#3D_human_whole_body)

    - [3D human body](#3D_human_body)

    - [3d human face](#3d_human_face)

    - [3d human head](#3d_human_head)

    - [3D human hand](#3D_human_hand)

    - [3d cloth](#3d_cloth)

    - [3d hair](#3d_hair)

    - [3d teeth](#3d_teeth)

    - [3d eyelids](#3d_eyelids)

 - [related papers](#related)

   - [human mattting](#human_mattting)

   - [pose estimation](#pose_estimation)

   - [registration](#registration)

   - [correspondence](#correspondence)

   - [application](#application)

   - [texture](#texture)

   - [skin](#skin)

   - [talking head](#talking_head)

   - [uncategorized](#uncategorized)

 - [parametric model](#parametric-model)

   - [body](#body)

   - [face](#face)

   - [head](#head)

   - [hand](#hand)

   - [method](#method)

 - [dataset](#dataset)

   - [face](#face)

   - [hand](#hand)

   - [body](#body)

   - [method](#method)

 - [others](#others)

 - [labs](#labs)

 - [other related awesome](#other-related-awesome)

 - [survey](#survey)

 

 

 

 

## 3d human

### AIGC

##### • Rodin: A Generative Model for Sculpting 3D Digital Avatars Using Diffusion  [paper](https://arxiv.org/abs/2212.06135)

##### • DreamFace: Progressive Generation of Animatable 3D Faces under Text Guidance  [paper](https://arxiv.org/abs/2304.03117)

##### • High-fidelity 3D Face Generation from Natural Language Descriptions

##### • Make-A-Character: High Quality Text-to-3D Character Generation within Minutes [code](https://github.com/Human3DAIGC/Make-A-Character)

### nerf_pifu_3dgs

##### • StereoPIFu: Depth Aware Clothed Human Digitization via Stereo Vision  [paper](https://arxiv.org/pdf/2104.05289.pdf)

##### • Learning Implicit 3D Representations of Dressed Humans from Sparse Views  [paper](https://arxiv.org/pdf/2104.08013v1.pdf)

##### • Animatable Neural Radiance Fields for Human Body Modeling  [paper](https://arxiv.org/pdf/2105.02872.pdf)

##### • PaMIR: Parametric Model-Conditioned Implicit Representation for Image-based Human Reconstruction  [paper](https://arxiv.org/pdf/2007.03858.pdf)  [code](https://github.com/ZhengZerong/PaMIR)

##### • Neural Actor: Neural Free-view Synthesis of Human Actors with Pose Control  [paper&code](http://gvv.mpi-inf.mpg.de/projects/NeuralActor/)

##### • MoCo-Flow: Neural Motion Consensus Flow for Dynamic Humans in Stationary Monocular Cameras  [paper](https://arxiv.org/pdf/2106.04477v1.pdf)

##### • DoubleField: Bridging the Neural Surface and Radiance Fields for High-fidelity Human Rendering  [paper](https://arxiv.org/pdf/2106.03798.pdf)

##### • Bridge the Gap Between Model-based and Model-free Human Reconstruction  [paper](https://arxiv.org/pdf/2106.06415v1.pdf)

##### • MetaAvatar: Learning Animatable Clothed Human Models from Few Depth Images  [paper](https://arxiv.org/pdf/2106.11944v1.pdf)

##### • Animatable Neural Radiance Fields from Monocular RGB Video  [paper](https://arxiv.org/pdf/2106.13629v1.pdf)

##### • Few-shot Neural Human Performance Rendering from Sparse RGBD Videos  [paper](https://arxiv.org/pdf/2107.06505v1.pdf)

##### • Relightable Neural Video Portrait  [paper](https://arxiv.org/pdf/2107.14735v1.pdf)

##### • FLAME-in-NeRF : Neural control of Radiance Fields for Free View Face Animation  [paper](https://arxiv.org/pdf/2108.04913v1.pdf)

##### • ARCH++: Animation-Ready Clothed Human Reconstruction Revisited  [paper](https://arxiv.org/pdf/2108.07845.pdf)

##### • Neural-GIF: Neural Generalized Implicit Functions for Animating People in Clothing  [paper](https://virtualhumans.mpi-inf.mpg.de/neuralgif/)

##### • Neural Human Performer: Learning Generalizable Radiance Fields for Human Performance Rendering  [paper](https://arxiv.org/pdf/2109.07448v1.pdf)  [code](https://youngjoongunc.github.io/nhp/)

##### • Topologically Consistent Multi-View Face Inference Using Volumetric Sampling  [paper](https://arxiv.org/pdf/2110.02948.pdf)

##### • Creating and Reenacting Controllable 3D Humans with Differentiable Rendering  [paper](https://arxiv.org/pdf/2110.11746v1.pdf)

##### • H-NeRF: Neural Radiance Fields for Rendering and Temporal Reconstruction of Humans in Motion  [paper](https://arxiv.org/pdf/2110.13746v1.pdf)

##### • FENeRF: Face Editing in Neural Radiance Fields  [paper](https://arxiv.org/pdf/2111.15490v1.pdf)

##### • LatentHuman: Shape-and-Pose Disentangled Latent Representation for Human Bodies  [paper&code](https://latenthuman.github.io/)

##### • Neural Head Avatars from Monocular RGB Videos  [paper](https://arxiv.org/pdf/2112.01554v1.pdf)

##### • HumanNeRF: Generalizable Neural Human Radiance Field from Sparse Inputs  [paper](https://arxiv.org/pdf/2112.02789v1.pdf)

##### • Implicit Neural Deformation for Multi-View Face Reconstruction  [paper](https://arxiv.org/pdf/2112.02494v1.pdf)

##### • MoFaNeRF: Morphable Facial Neural Radiance Field  [paper](https://arxiv.org/pdf/2112.02308.pdf)  [code](https://github.com/zhuhao-nju/mofanerf)

##### • Geometry-Guided Progressive NeRF for Generalizable and Efficient Neural Human Rendering  [paper](https://arxiv.org/pdf/2112.04312v1.pdf)

##### • HeadNeRF: A Real-time NeRF-based Parametric Head Model  [paper](https://arxiv.org/pdf/2112.05637v1.pdf)  [code](https://github.com/CrisHY1995/headnerf)

##### • I M Avatar: Implicit Morphable Head Avatars from Videos  [paper](https://arxiv.org/pdf/2112.07471v1.pdf)  [code](https://github.com/zhengyuf/IMavatar)

##### • LookinGoodπ: Real-time Person-independent Neural Re-rendering for High-quality Human Performance Capture  [paper](https://arxiv.org/pdf/2112.08037v1.pdf)

##### • ICON: Implicit Clothed humans Obtained from Normals  [paper](https://arxiv.org/pdf/2112.09127v1.pdf)  [code](https://github.com/YuliangXiu/ICON)

##### • DD-NeRF: Double-Diffusion Neural Radiance Field as a Generalizable Implicit Body Representation  [paper](https://arxiv.org/pdf/2112.12390v1.pdf)

##### • Human View Synthesis using a Single Sparse RGB-D Input  [paper](https://arxiv.org/pdf/2112.13889v1.pdf)

##### • Surface-Aligned Neural Radiance Fields for Controllable 3D Human Synthesis  [paper](https://arxiv.org/pdf/2201.01683v1.pdf)

##### • Embodied Hands: Modeling and Capturing Hands and Bodies Together  [paper](https://arxiv.org/pdf/2201.02610v1.pdf)

##### • HumanNeRF: Free-viewpoint Rendering of Moving People from Monocular Video  [paper](https://arxiv.org/pdf/2201.04127v1.pdf) [code](https://github.com/chungyiweng/humannerf)

##### • gDNA: Towards Generative Detailed Neural Avatars  [paper](https://arxiv.org/pdf/2201.04123v1.pdf)  [code](https://github.com/xuchen-ethz/gdna)

##### • SelfRecon: Self Reconstruction Your Digital Avatar from Monocular Video  [paper](https://arxiv.org/pdf/2201.12792v1.pdf)

##### •  NeuVV: Neural Volumetric Videos with Immersive Rendering and Editing  [paper](https://arxiv.org/pdf/2202.06088v1.pdf)

##### •  Animatable Neural Radiance Fields for Modeling Dynamic Human Bodies [paper](https://arxiv.org/abs/2105.02872)  [code](https://github.com/zju3dv/animatable_nerf)

##### •  DeepMultiCap: Performance Capture of Multiple Characters Using Sparse Multiview Cameras  [paper](https://arxiv.org/abs/2105.00261)  [code](https://github.com/DSaurus/DeepMultiCap)

##### •  NeuralFusion: Neural Volumetric Rendering under Human-object Interactions  [paper](https://arxiv.org/pdf/2202.12825v1.pdf)

##### •  PINA: Learning a Personalized Implicit Neural Avatar from a Single RGB-D Video Sequence  [paper](https://arxiv.org/pdf/2203.01754v1.pdf)  [code](https://github.com/zj-dong/pina/tree/page)

##### •  NeuMan: Neural Human Radiance Field from a Single Video  [paper](https://arxiv.org/pdf/2203.12575v1.pdf)

##### •   M Avatar: Implicit Morphable Head Avatars from Videos  [paper](https://arxiv.org/pdf/2112.07471.pdf)  [code](https://github.com/zhengyuf/IMavatar)

##### •   ImFace: A Nonlinear 3D Morphable Face Model with Implicit Neural Representations  [paper](https://arxiv.org/pdf/2203.14510.pdf)

##### •   COAP: Compositional Articulated Occupancy of People  [paper](https://arxiv.org/pdf/2204.06184v1.pdf)  [code](https://github.com/markomih/COAP)

##### •   SunStage: Portrait Reconstruction and Relighting using the Sun as a Light Stage  [paper](https://arxiv.org/pdf/2204.03648v1.pdf)

##### •  LISA: Learning Implicit Shape and Appearance of Hands  [paper](https://arxiv.org/pdf/2204.01695v1.pdf)

##### •  Animatable Neural Radiance Fields from Monocular RGB-D  [paper](https://arxiv.org/pdf/2204.01218v1.pdf)

##### •  JIFF: Jointly-aligned Implicit Face Function for High Quality Single View Clothed Human Reconstruction  [paper](https://arxiv.org/pdf/2204.10549v1.pdf)

##### •  Generalizable Neural Performer: Learning Robust Radiance Fields for Human Novel View Synthesis  [paper](https://arxiv.org/pdf/2204.11798v1.pdf)

##### •  DANBO: Disentangled Articulated Neural Body Representations via Graph Neural Networks  [paper](https://arxiv.org/pdf/2205.01666.pdf)

##### •  Single-view 3D Body and Cloth Reconstruction under Complex Poses  [paper](https://arxiv.org/pdf/2205.04087v1.pdf)

##### •  KeypointNeRF: Generalizing Image-based Volumetric Avatars using Relative Spatial Encoding of Keypoints  [paper](https://arxiv.org/pdf/2205.04992.pdf)

##### •  H3D-Net: Few-Shot High-Fidelity 3D Head Reconstruction  [paper](https://arxiv.org/pdf/2107.12512.pdf)  [code](https://github.com/MaxPolak97/H3D-Net-reproduction)

##### • Photorealistic Monocular 3D Reconstruction of Humans Wearing Clothing  [paper](https://arxiv.org/abs/2204.08906)

##### • High-Fidelity Human Avatars from a Single RGB Camera  [paper](https://github.com/hzhao1997/HF-Avatar)

##### • UV Volumes for Real-time Rendering of Editable Free-view Human Performance  [code](https://github.com/fanegg/UV-Volumes)

##### • FOF: Learning Fourier Occupancy Field for Monocular Real-time Human Reconstruction  [paper](https://arxiv.org/pdf/2206.02194v1.pdf)

##### • NeMF: Neural Motion Fields for Kinematic Animation  [paper](https://arxiv.org/pdf/2206.03287v1.pdf)

##### • RigNeRF: Fully Controllable Neural 3D Portraits  [paper](https://arxiv.org/pdf/2206.06481v1.pdf)

##### • EyeNeRF: A Hybrid Representation for Photorealistic Synthesis, Animation and Relighting of Human Eyes  [paper](https://arxiv.org/pdf/2206.08428v1.pdf)

##### • TAVA: Template-free Animatable Volumetric Actors  [paper](https://arxiv.org/pdf/2206.08929v1.pdf)

##### • Neural Surface Reconstruction of Dynamic Scenes with Monocular RGB-D Camera  [homepage](https://ustc3dv.github.io/ndr/)

##### • Generative Neural Articulated Radiance Fields  [paper](https://arxiv.org/pdf/2206.14314v1.pdf)

##### • Neural Parameterization for Dynamic Human Head Editing [paper](https://arxiv.org/pdf/2207.00210v1.pdf)

##### • AvatarCap: Animatable Avatar Conditioned Monocular Human Volumetric Capture  [paper](https://arxiv.org/pdf/2207.02031v1.pdf)  [code](https://github.com/lizhe00/AvatarCap)

##### • Learning Implicit Templates for Point-Based Clothed Human Modeling  [homepage](https://jsnln.github.io/fite/)

##### •Relighting4D: Neural Relightable Human from Videos  [code](https://github.com/FrozenBurning/Relighting4D)

##### •High Quality Human Reconstruction via Diffusion-based Stereo Using Sparse Cameras  [paper](https://arxiv.org/pdf/2207.08000v1.pdf)

##### •CrossHuman: Learning Cross-Guidance from Multi-Frame Images for Human Reconstruction  [paper](https://arxiv.org/pdf/2207.09735v1.pdf)

##### •UNIF: United Neural Implicit Functions for Clothed Human Reconstruction and Animation  [paper](https://arxiv.org/pdf/2207.09835v1.pdf)  [code](https://github.com/ShenhanQian/UNIF)

##### •Drivable Volumetric Avatars using Texel-Aligned Features  [paper](https://arxiv.org/pdf/2207.09774v1.pdf)

##### •The One Where They Reconstructed 3D Humans and Environments in TV Shows  [homepage](https://ethanweber.me/sitcoms3D/)

##### •AvatarGen: a 3D Generative Model for Animatable Human Avatars  [paper](https://arxiv.org/pdf/2208.00561.pdf)

##### •VolTeMorph: Realtime, Controllable and Generalisable Animation of Volumetric Representations  [paper](https://www.arxiv-vanity.com/papers/2208.00949/?continueFlag=acd9680585ca1db48ed3cbc277e4da97)

##### •Multi-NeuS: 3D Head Portraits from Single Image with Neural Implicit Functions  [paper](https://arxiv.org/pdf/2209.04436.pdf)

##### •Learning to Relight Portrait Images via a Virtual Light Stage and Synthetic-to-Real Adaptation  [paper](https://arxiv.org/pdf/2209.10510.pdf)

##### •Occupancy Planes for Single-view RGB-D Human Reconstruction Xiaoming Zhao, Yuan-Ting Hu, Zhongzheng Ren, Alexander G. Schwing  [paper](https://arxiv.org/pdf/2208.02817.pdf)

##### •ManVatar : Fast 3D Head Avatar Reconstruction Using Motion-Aware Neural Voxels  [paper](https://arxiv.org/pdf/2211.13206.pdf)

##### •NeuS2: Fast Learning of Neural Implicit Surfaces for Multi-view Reconstruction  [paper](https://arxiv.org/pdf/2212.05231.pdf)

##### •Structured 3D Features for Reconstructing Relightable and Animatable Avatars  [project](https://enriccorona.github.io/s3f/)

##### •PhoMoH: Implicit Photorealistic 3D Models of Human Heads  [paper](https://arxiv.org/pdf/2212.07275.pdf)

##### •NerfCap: Human Performance Capture With Dynamic Neural Radiance Fields  [paper](http://www.cad.zju.edu.cn/home/gfzhang/papers/NerfCap/NerfCap_TVCG_2022.pdf)  [code](https://github.com/wangkangkan/nerfcap)

##### •ECON: Explicit Clothed humans Obtained from Normals  [homepage](https://xiuyuliang.cn/econ/)

##### •PointAvatar: Deformable Point-based Head Avatars from Videos  [homepage](https://zhengyuf.github.io/pointavatar/)

##### •TotalSelfScan: Learning Full-body Avatars from Self-Portrait Videos of Faces, Hands, and Bodies  [project](https://zju3dv.github.io/TotalSelfScan/)

##### •InstantAvatar: Learning Avatars from Monocular Video in 60 Seconds  [homepage](https://tijiang13.github.io/InstantAvatar/#)

##### •HumanGen: Generating Human Radiance Fields with Explicit Priors [paper](https://arxiv.org/pdf/2212.05321v1.pdf)

##### • GazeNeRF: 3D-Aware Gaze Redirection with Neural Radiance Fields  [paper](https://www.arxivdaily.com/thread/35452)

##### • Pixel2ISDF: Implicit Signed Distance Fields based Human Body Model from Multi-view and Multi-pose Images  [paper](https://arxiv.org/pdf/2212.02765v1.pdf)

##### • Learning Neural Parametric Head Models  [homepage](https://simongiebenhain.github.io/NPHM/)

##### • RANA: Relightable Articulated Neural Avatars  [paper](https://arxiv.org/pdf/2212.03237v1.pdf)

##### • One-shot Implicit Animatable Avatars with Model-based Priors   [paper](https://arxiv.org/pdf/2212.02469v1.pdf)

##### • Super-resolution 3D Human Shape from a Single Low-Resolution Image  [paper](https://marcopesavento.github.io/SuRS/eccv22_main.pdf)  [code](https://github.com/marcopesavento/Super-resolution-3D-Human-Shape-from-a-Single-Low-Resolution-Image)

##### • Vid2Avatar: 3D Avatar Reconstruction from Videos in the Wild via Self-supervised Scene Decomposition  [paper](https://ait.ethz.ch/projects/2023/vid2avatar/downloads/main.pdf)

##### • X-Avatar: Expressive Human Avatars  [github](https://github.com/Skype-line/X-Avatar)

##### • Learning Neural Volumetric Representations of Dynamic Humans in Minutes  [paper&code](https://zju3dv.github.io/instant_nvr/) 

##### • NeRSemble: Multi-view Radiance Field Reconstruction of Human Heads  [paper](https://arxiv.org/abs/2305.03027)

##### • PICA: Physics-Integrated Clothed Avatar [paper](https://arxiv.org/pdf/2407.05324)

### geo_fusion

##### • DoubleFusion: Real-time Capture of Human Performances with Inner Body Shapes from a Single Depth Sensor  [paper](https://arxiv.org/abs/1804.06023)

##### • Robust 3D Self-portraits in Seconds  [paper](https://arxiv.org/abs/2004.02460)

##### • ACCURATE HUMAN BODY RECONSTRUCTION FOR VOLUMETRIC VIDEO  [paper](https://arxiv.org/pdf/2202.13118v1.pdf)

##### • OcclusionFusion: Occlusion-aware Motion Estimation for Real-time Dynamic 3D Reconstruction [paper](https://arxiv.org/pdf/2203.07977v1.pdf)  [code](https://github.com/wenbin-lin/OcclusionFusion/)

### photo

##### • Portrait Reconstruction and Relighting using the Sun as a Light Stage  [homepage](https://grail.cs.washington.edu/projects/sunstage/)

##### • Reconstructing Hand-Held Objects from Monocular Video  [paper](https://arxiv.org/pdf/2211.16835v1.pdf)

##### • In-Hand 3D Object Scanning from an RGB Sequence  [paper](https://arxiv.org/pdf/2211.16193v1.pdf)

### 3D_human_whole_body

##### • Monocular Expressive Body Regression through Body-Driven Attention  [paper](https://arxiv.org/abs/2008.09062)  [code](https://github.com/vchoutas/expose)

##### • FrankMocap: Fast Monocular 3D Hand and Body Motion Capture by Regression and Integration  [paper](https://arxiv.org/pdf/2008.08324.pdf)  [code](https://github.com/facebookresearch/frankmocap)

##### • Collaborative Regression of Expressive Bodies using Moderation  [paper&code](https://pixie.is.tue.mpg.de/)

##### • Monocular Real-time Full Body Capture with Inter-part Correlations  [paper&code](https://calciferzh.github.io/publications/zhou2021monocular)

##### • Monocular Real-time Hand Shape and Motion Capture using Multi-modal Data  [paper&code](https://calciferzh.github.io/publications/zhou2020monocular)

##### • Real-time RGBD-based Extended Body Pose Estimation  [paper](https://arxiv.org/pdf/2103.03663.pdf)  [code](https://github.com/rmbashirov/rgbd-kinect-pose)

##### • Detailed Avatar Recovery from Single Image  [paper](https://arxiv.org/pdf/2108.02931v1.pdf)

##### • Lightweight Multi-person Total Motion Capture Using Sparse Multi-view Cameras  [paper](https://arxiv.org/pdf/2108.10378v1.pdf)

##### • Imposing Temporal Consistency on Deep Monocular Body Shape and Pose Estimation  [paper](https://arxiv.org/pdf/2202.03074v1.pdf)

##### • PIANO: A Parametric Hand Bone Model from Magnetic Resonance Imaging  [github](https://github.com/reyuwei/PIANO_model)

##### • GOAL: Generating 4D Whole-Body Motion for Hand-Object Grasping  [paper](https://arxiv.org/pdf/2112.11454.pdf)  [code](https://github.com/otaheri/GOAL)

##### • PyMAF-X: Towards Well-aligned Full-body Model Regression from Monocular Images  [paper](https://arxiv.org/pdf/2207.06400v1.pdf)

##### • Generating Holistic 3D Human Motion from Speech  [project](https://talkshow.is.tue.mpg.de/)

##### • One-Stage 3D Whole-Body Mesh Recovery with Component Aware Transformer [project](https://osx-ubody.github.io/)

### 3D_human_body

##### • Pose2Mesh: Graph Convolutional Network for 3D Human Pose and Mesh Recovery from a 2D Human Pose  [paper](https://arxiv.org/abs/2008.09047)  [code](https://github.com/hongsukchoi/Pose2Mesh_RELEASE)

##### • Monocular Real-Time Volumetric Performance Capture  [paper](https://arxiv.org/abs/2007.13988)  [code](https://github.com/Project-Splinter/MonoPort)

##### • Full-Body Awareness from Partial Observations  [paper](https://arxiv.org/abs/2008.06046)  [code](https://github.com/crockwell/partial_humans)

##### • CenterHMR: a Bottom-up Single-shot Method for Multi-person 3D Mesh Recovery from a Single Image  [paper](https://arxiv.org/pdf/2008.12272.pdf)  [code](https://github.com/Arthur151/CenterHMR)

##### • Reconstructing NBA players  [paper](https://arxiv.org/pdf/2007.13303.pdf)  [code](https://github.com/luyangzhu/NBA-Players)

##### • Going beyond Free Viewpoint: Creating Animatable Volumetric Video of Human Performances  [paper](https://arxiv.org/abs/2009.00922)

##### • Synthetic Training for Accurate 3D Human Pose and Shape Estimation in the Wild  [paper](https://arxiv.org/pdf/2009.10013.pdf)  [code](https://github.com/akashsengupta1997/STRAPS-3DHumanShapePose)

##### • Implicit 3D Human Mesh Recovery using Consistency with Pose and Shape from Unseen-view  [paper](https://arxiv.org/abs/2306.17651)

##### • Diff-HMR: Generative Approach for Probabilistic Human Mesh Recovery using Diffusion Models  [paper](https://arxiv.org/abs/2308.02963)  [code](https://github.com/hanbyel0105/Diff-HMR)

##### • Video Inference for Human Mesh Recovery with Vision Transformer  [paper](https://ieeexplore.ieee.org/document/10042731)

##### • MonoClothCap: Towards Temporally Coherent Clothing Capture from Monocular RGB Video  [paper](https://arxiv.org/pdf/2009.10711.pdf)

##### • Multi-View Consistency Loss for Improved Single-Image 3D Reconstruction of Clothed People  [paper](https://arxiv.org/abs/2009.14162)  [code](https://akincaliskan3d.github.io/MV3DH/)

##### • Synthetic Training for Monocular Human Mesh Recovery  [paper](https://arxiv.org/abs/2010.14036)

##### • Pose2Pose: 3D Positional Pose-Guided 3D Rotational Pose Prediction for Expressive 3D Human Pose and Mesh Estimation  [paper](https://arxiv.org/pdf/2011.11534.pdf)

##### • Deep Physics-aware Inference of Cloth Deformation for Monocular Human Performance Capture

##### • 4D Human Body Capture from Egocentric Video via 3D Scene Grounding  [paper](https://arxiv.org/abs/2011.13341)

##### • HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimation  [paper](https://arxiv.org/pdf/2011.14672.pdf)  [code](https://github.com/Jeff-sjtu/HybrIK)

##### • We are More than Our Joints: Predicting how 3D Bodies Move  [paper](https://arxiv.org/pdf/2012.00619.pdf)

##### • SMPLy Benchmarking 3D Human Pose Estimation in the Wild  [paper](https://arxiv.org/pdf/2012.02743v1.pdf)

##### • Synthesizing Long-Term 3D Human Motion and Interaction in 3D  [paper](https://jiashunwang.github.io/Long-term-Motion-in-3D-Scenes/)

##### • Detailed 3D Human Body Reconstruction from Multi-view Images Combining Voxel Super-Resolution and Learned Implicit Representation

##### • A novel joint points and silhouette-based method to estimate 3D human pose and shape

##### • FaceDet3D: Facial Expressions with 3D Geometric Detail Prediction  [paper](https://arxiv.org/pdf/2012.07999.pdf)

##### • NerFACE: Dynamic Neural Radiance Fields for Monocular 4D Facial Avatar Reconstruction  [code](https://github.com/gafniguy/4D-Facial-Avatars)

##### • Learning Complex 3D Human Self-Contact  [paper](https://arxiv.org/pdf/2012.10366.pdf)

##### • Populating 3D Scenes by Learning Human-Scene Interaction  [paper](https://arxiv.org/pdf/2012.11581.pdf)

##### • ANR: Articulated Neural Rendering for Virtual Avatars  [paper](https://anr-avatars.github.io/)

##### • Human Mesh Recovery from Multiple Shots   [paper](https://geopavlakos.github.io/multishot/)

##### • Lifting 2D StyleGAN for 3D-Aware Face Generation  [paper](S3: Neural Shape, Skeleton, and Skinning Fields for 3D Human Modeling)

##### • Capturing Detailed Deformations of Moving Human Bodies  [paper](https://arxiv.org/pdf/2102.07343.pdf)

##### • 3D Human Pose, Shape and Texture from Low-Resolution Images and Videos  [paper](https://arxiv.org/pdf/2103.06498v1.pdf)

##### • ChallenCap: Monocular 3D Capture of Challenging Human Performances using Multi-Modal References  [paper](https://arxiv.org/pdf/2103.06747v1.pdf)

##### • SMPLicit: Topology-aware Generative Model for Clothed People  [paper&code](http://www.iri.upc.edu/people/ecorona/smplicit/)

##### • Learning High Fidelity Depths of Dressed Humans by Watching Social Media Dance Videos  [paper](https://arxiv.org/pdf/2103.03319.pdf)

##### • NeuralHumanFVV: Real-Time Neural Volumetric Human Performance Rendering using RGB Cameras  [paper](https://arxiv.org/pdf/2103.07700v1.pdf)

##### • Probabilistic 3D Human Shape and Pose Estimation from Multiple Unconstrained Images in the Wild  [paper](https://arxiv.org/pdf/2103.10978v1.pdf)

##### • 3DCrowdNet: 2D Human Pose-Guided 3D Crowd Human Pose and Shape Estimation in the Wild  [paper](https://arxiv.org/pdf/2104.07300v1.pdf)

##### • SCALE: Modeling Clothed Humans with a Surface Codec of Articulated Local Elements  [paper](https://arxiv.org/pdf/2104.07660.pdf)

##### • Multi-person Implicit Reconstruction from a Single Image  [paper](https://arxiv.org/pdf/2104.09283v1.pdf)

##### • PARE: Part Attention Regressor for 3D Human Body Estimation  [paper](https://arxiv.org/pdf/2104.08527v1.pdf)  [code](https://pare.is.tue.mpg.de/)

##### • Temporal Consistency Loss for High Resolution Textured and Clothed 3D Human Reconstruction from Monocular Video  [paper](https://arxiv.org/pdf/2104.09259.pdf)

##### • Function4D: Real-time Human Volumetric Capture from Very Sparse Consumer RGBD Sensors  [paper](http://www.liuyebin.com/Function4D/Function4D.html)

##### • End-to-End Human Pose and Mesh Reconstruction with Transformers  [paper](https://github.com/microsoft/MeshTransformer)

##### • Revitalizing Optimization for 3D Human Pose and Shape Estimation: A Sparse Constrained Formulation  [paper](https://arxiv.org/pdf/2105.13965v1.pdf)

##### • SHARP: Shape-Aware Reconstruction of People In Loose Clothing  [paper](https://arxiv.org/pdf/2106.04778v1.pdf)

##### • THUNDR: Transformer-based 3D HUmaN Reconstruction with Markers  [paper](https://arxiv.org/pdf/2106.09336v1.pdf)

##### • Deep3DPose: Realtime Reconstruction of Arbitrarily Posed Human Bodies from Single RGB Images  [paper](https://arxiv.org/pdf/2106.11536v1.pdf)

##### • Learning Local Recurrent Models for Human Mesh Recovery  [paper](https://arxiv.org/pdf/2107.12847v1.pdf)

##### • PoseFusion2: Simultaneous Background Reconstruction and Human Shape Recovery in Real-time  [paper](https://arxiv.org/pdf/2108.00695v1.pdf)

##### • LASOR: Learning Accurate 3D Human Pose and Shape Via Synthetic Occlusion-Aware Data and Neural Mesh Rendering  [paper](https://arxiv.org/pdf/2108.00351v1.pdf)

##### • Learning Motion Priors for 4D Human Body Capture in 3D Scenes  [paper](https://arxiv.org/pdf/2108.10399v1.pdf)  [code](https://github.com/sanweiliti/LEMO)

##### • Probabilistic Modeling for Human Mesh Recovery  [paper&code](https://www.seas.upenn.edu/~nkolot/projects/prohmr/)

##### • DC-GNet: Deep Mesh Relation Capturing Graph Convolution Network for 3D Human Shape Reconstruction  [paper](https://arxiv.org/pdf/2108.12384v1.pdf)

##### • Encoder-decoder with Multi-level Attention for 3D Human Shape and Pose Estimation  [paper](https://arxiv.org/pdf/2109.02303v1.pdf)  [code](https://github.com/ziniuwan/maed)

##### • Action-Conditioned 3D Human Motion Synthesis with Transformer VAE  [code](https://github.com/Mathux/ACTOR)

##### • Learning to Regress Bodies from Images using Differentiable Semantic Rendering  [paper](https://arxiv.org/pdf/2110.03480v1.pdf)

##### • Deep Two-Stream Video Inference for Human Body Pose and Shape Estimation  [paper](https://arxiv.org/pdf/2110.11680v1.pdf)

##### • UltraPose: Synthesizing Dense Pose with 1 Billion Points by Human-body Decoupling 3D Model  [paper](https://arxiv.org/pdf/2110.15267v1.pdf)

##### • Body Size and Depth Disambiguation in Multi-Person Reconstruction from Single Images  [paper](https://arxiv.org/pdf/2111.01884v1.pdf)  [code](https://github.com/nicolasugrinovic/size_depth_disambiguation)

##### • Unified 3D Mesh Recovery of Humans and Animals by Learning Animal Exercise  [paper](https://arxiv.org/pdf/2111.02450v1.pdf)

##### • 3D Human Shape and Pose from a Single Low-Resolution Image with Self-Supervised Learning  [paper](https://arxiv.org/pdf/2007.13666.pdf)  [code](https://github.com/xuxy09/RSC-Net)

##### • Out-of-Domain Human Mesh Reconstruction via Bilevel Online Adaptation  [paper](https://drive.google.com/file/d/1b6e3rMrVn_xNhM-MitqpLtulARdl4M9F/view?usp=sharing)  [code](https://www.google.com/url?q=https%3A%2F%2Fgithub.com%2Fsyguan96%2FDynaBOA&sa=D&sntz=1&usg=AFQjCNHYmgSyYqdKGYNp7W-bAO2MrHfp1w)

##### • MeshLeTemp: Leveraging the Learnable Vertex-Vertex Relationship to Generalize Human Pose and Mesh Reconstruction for In-the-Wild Scenes  [paper](https://arxiv.org/pdf/2202.07228v1.pdf)

##### • Monocular Human Shape and Pose with Dense Mesh-borne Local Image Features  [paper](https://arxiv.org/pdf/2111.05319v1.pdf)

##### • Human Performance Capture from Monocular Video in the Wild  [paper](https://arxiv.org/pdf/2111.14672.pdf)

##### • Probabilistic Estimation of 3D Human Shape and Pose with a Semantic Local Parametric Model  [paper](https://arxiv.org/pdf/2111.15404v1.pdf)

##### • GLAMR: Global Occlusion-Aware Human Mesh Recovery with Dynamic Cameras  [paper](https://arxiv.org/pdf/2112.01524v1.pdf)  [code](https://github.com/NVlabs/GLAMR)

##### • MetaAvatar: Learning Animatable Clothed Human Models from Few Depth Images}  [paper](https://openreview.net/forum?id=Q-PA3D1OsDz)  [code](https://github.com/taconite/MetaAvatar-release)

##### • EgoBody: Human Body Shape, Motion and Social Interactions from Head-Mounted Devices  [paper](https://arxiv.org/pdf/2112.07642v1.pdf)  [code](https://sanweiliti.github.io/egobody/egobody.html)

##### • Putting People in their Place: Monocular Regression of 3D People in Depth  [paper](https://arxiv.org/pdf/2112.08274v1.pdf)

##### • Multi-initialization Optimization Network for Accurate 3D Human Pose and Shape Estimation  [paper](https://arxiv.org/pdf/2112.12917v1.pdf)

##### • moothNet: A Plug-and-Play Network for Refining Human Poses in Videos  [paper](https://arxiv.org/pdf/2112.13715v1.pdf)

##### • HSPACE: Synthetic Parametric Humans Animated in Complex Environments  [paper](https://arxiv.org/pdf/2112.12867v1.pdf)

##### • VoteHMR: Occlusion-Aware Voting Network for Robust 3D Human Mesh Recovery from Partial Point Clouds  [paper](https://arxiv.org/pdf/2110.08729.pdf)  [code](https://github.com/hanabi7/VoteHMR)

##### • H4D: Human 4D Modeling by Learning Neural Compositional Representation  [paper](https://arxiv.org/pdf/2203.01247v1.pdf)

##### • Capturing Humans in Motion: Temporal-Attentive 3D Human Pose and Shape Estimation from Monocular Video  [paper](https://arxiv.org/pdf/2203.08534v1.pdf)  [code](https://mps-net.github.io/MPS-Net/)

##### • HybridCap: Inertia-aid Monocular Capture of Challenging Human Motions  [paper](https://arxiv.org/pdf/2203.09287v1.pdf)

##### • Learning to Estimate Robust 3D Human Mesh from In-the-Wild Crowded Scenes  [paper](https://arxiv.org/abs/2104.07300)  [code](https://github.com/hongsukchoi/3DCrowdNet_RELEASE)

##### • BodySLAM: Joint Camera Localisation, Mapping, and Human Motion Tracking  [paper](https://arxiv.org/pdf/2205.02301v1.pdf)

##### • HULC: 3D Human Motion Capture with Pose Manifold Sampling and Dense Contact Guidance  [paper](https://arxiv.org/pdf/2205.05677v1.pdf)

##### • Learned Vertex Descent: A New Direction for 3D Human Model Fitting  [paper](https://arxiv.org/pdf/2205.06254v1.pdf)  [code](https://github.com/enriccorona/LVD)

##### • MUG: Multi-human Graph Network for 3D Mesh Reconstruction from 2D Pose  [paper](https://www.arxivdaily.com/thread/26950)

##### • Accurate 3D Body Shape Regression using Metric and Semantic Attributes  [paper](https://arxiv.org/pdf/2206.07036v1.pdf)

##### • Capturing and Inferring Dense Full-Body Human-Scene Contact  [homepage](https://rich.is.tue.mpg.de/index.html)

##### • Occluded Human Body Capture with Self-Supervised Spatial-Temporal Motion Prior  [paper](https://arxiv.org/pdf/2207.05375v1.pdf)

##### • Live Stream Temporally Embedded 3D Human Body Pose and Shape Estimation  [paper](https://arxiv.org/pdf/2207.12537v1.pdf)  [code](https://github.com/ostadabbas/TePose)

##### • CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape Estimation  [paper](https://arxiv.org/pdf/2208.00571.pdf)

##### • FastMETRO: Cross-Attention of Disentangled Modalities for 3D Human Mesh Recovery with Transformers  [paper](https://arxiv.org/pdf/2207.13820.pdf)

##### • Parametric Model Estimation for 3D Clothed Humans from Point Clouds  [paper](http://www.cad.zju.edu.cn/home/gfzhang/papers/ISMAR2021_3DClothedHumans/3DClothedHumans.pdf) [code](https://github.com/wangkangkan/3DClothedHumans)

##### • Scene-Aware 3D Multi-Human Motion Capture from a Single Camera  [paper](https://arxiv.org/pdf/2301.05175v1.pdf)  [code](https://github.com/dluvizon/scene-aware-3d-multi-human)

##### • NeMo: 3D Neural Motion Fields from Multiple Video Instances of the Same Action [homepage](https://sites.google.com/view/nemo-neural-motion-field?pli=1)

##### • IKOL: Inverse kinematics optimization layer for 3D human pose and shape estimation via Gauss-Newton differentiation  [paper](https://arxiv.org/pdf/2302.01058.pdf)  [code](https://github.com/Juzezhang/IKOL)

### 3d_human_face

##### • High-Fidelity 3D Digital Human Creation from RGB-D Selfies  [paper](https://arxiv.org/pdf/2010.05562.pdf)  [code](https://github.com/tencent-ailab/hifi3dface)

##### • StyleUV: Diverse and High-quality UV Map Generative Model  [paper](https://arxiv.org/pdf/2011.12893.pdf)

##### • i3DMM: Deep Implicit 3D Morphable Model of Human Heads  [paper](https://arxiv.org/pdf/2011.14143v1.pdf)

##### • Relightable 3D Head Portraits from a Smartphone Video  [paper](https://arxiv.org/pdf/2012.09963.pdf)

##### • Learning Compositional Radiance Fields of Dynamic Human Heads  [paper](https://arxiv.org/pdf/2012.09955.pdf)

##### • SIDER : Single-Image Neural Optimization for Facial Geometric Detail Recovery  [paper](https://arxiv.org/pdf/2108.05465v1.pdf)

##### • Synergy between 3DMM and 3D Landmarks for Accurate 3D Facial Geometry  [paper](https://arxiv.org/pdf/2110.09772.pdf)  [code](https://github.com/choyingw/SynergyNet)

##### • HIGH-QUALITY REAL TIME FACIAL CAPTURE BASED ON SINGLE CAMERA  [paper](https://arxiv.org/pdf/2111.07556v1.pdf)

##### • Self-supervised High-fidelity and Re-renderable 3D Facial Reconstruction from a Single Imag  [paper](https://arxiv.org/pdf/2111.08282.pdf)

##### • Generating Diverse 3D Reconstructions from a Single Occluded Face Image  [paper](https://arxiv.org/pdf/2112.00879v1.pdf)

##### • Self-Supervised Robustifying Guidance for Monocular 3D Face Reconstruction  [paper](https://arxiv.org/pdf/2112.14382v1.pdf)

##### • BabyNet: Reconstructing 3D faces of babies from uncalibrated photographs  [paper](https://arxiv.org/pdf/2203.05908v1.pdf)

##### • S2F2: Self-Supervised High Fidelity Face Reconstruction from Monocular Image  [paper](https://arxiv.org/pdf/2203.07732v1.pdf)

##### • Facial Geometric Detail Recovery via Implicit Representation  [paper](https://arxiv.org/pdf/2203.09692v1.pdf)  [code](https://github.com/deepinsight/insightface/tree/master/reconstruction/PBIDR)

##### • Beyond 3DMM: Learning to Capture High-fidelity 3D Face Shape  [paper](https://arxiv.org/pdf/2204.04379v1.pdf)

##### • From 2D Images to 3D Model: Weakly Supervised Multi-View Face Reconstruction with Deep Fusion  [paper](https://arxiv.org/pdf/2204.03842v1.pdf)

##### • F3D face reconstruction with dense landmarks  [paper](https://arxiv.org/pdf/2204.02776v1.pdf)

##### • EMOCA: Emotion Driven Monocular Face Capture and Animation  [paper](https://arxiv.org/pdf/2204.11312v1.pdf)

##### • Single-Image 3D Face Reconstruction under Perspective Projection  [paper](https://arxiv.org/pdf/2205.04126v1.pdf)

##### • AVFace: Towards Detailed Audio-Visual 4D Face Reconstruction  [paper](https://arxiv.org/pdf/2304.13115v1.pdf)

### 3d_human_head

##### • Auto-Card: Auto-CARD: Efficient and Robust Codec Avatar Driving for Real-time Mobile Telepresence  [paper](https://arxiv.org/abs/2304.11835)

##### • DECA: Detailed Expression Capture and Animation  [paper](https://arxiv.org/pdf/2012.04012.pdf) [code](https://github.com/YadiraF/DECA?utm_source=catalyzex.com)

##### • Pixel Codec Avatars  [paper](https://arxiv.org/pdf/2104.04638.pdf)

##### • H3D-Net: Few-Shot High-Fidelity 3D Head Reconstruction  [paper](https://arxiv.org/pdf/2107.12512v1.pdf)

##### •Towards Metrical Reconstruction of Human Faces  [paper](https://arxiv.org/pdf/2204.06607v1.pdf)  [code](https://zielon.github.io/mica/)

##### •Data-driven 3D human head reconstruction [paper](https://www.sciencedirect.com/science/article/abs/pii/S0097849319300317)

##### •Dynamic 3D avatar creation from hand-held video input, ACM  [paper](http://sofienbouaziz.com/pdf/Avatars_SIGG15.pdf)

##### •Realistic One-shot Mesh-based Head Avatars  [paper](https://arxiv.org/pdf/2206.08343.pdf)

##### •Authentic Volumetric Avatars from a Phone Scan  [paper](https://drive.google.com/file/d/1i4NJKAggS82wqMamCJ1OHRGgViuyoY6R/view)

##### •Neural Head Avatars from Monocular RGB Videos  [homepage](https://philgras.github.io/neural_head_avatars/neural_head_avatars.html)

##### •Towards Metrical Reconstruction of Human Faces  [homepage](https://zielon.github.io/mica/)

##### •High-Quality Facial Geometry and Appearance Capture at Home [code](https://github.com/yxuhan/CoRA)

### 3D_human_hand

##### • Active Learning for Bayesian 3D Hand Pose Estimation  [paper](https://arxiv.org/pdf/2010.00694.pdf)  [code](https://github.com/razvancaramalau/al_bhpe)

##### • Multi-View Consistency Loss for Improved Single-Image 3D Reconstruction of Clothed People  [paper](https://akincaliskan3d.github.io/MV3DH//resources/ACCV_Cam_Ready_Multi_View_3D_Human.pdf)  [code](https://github.com/akcalakcal/Multi_View_Consistent_Single_Image_3D_Human_Reconstruction)

##### • EventHands: Real-Time Neural 3D Hand Reconstruction from an Event Stream

##### • Monocular Real-time Full Body Capture with Inter-part Correlations

##### • Im2Mesh GAN: Accurate 3D Hand Mesh Recovery from a Single RGB Image

##### • HandTailor: Towards High-Precision Monocular 3D Hand Recovery  [paper](https://arxiv.org/pdf/2102.09244v1.pdf)  [code](https://github.com/LyuJ1998/HandTailor)

##### • Camera-Space Hand Mesh Recovery via Semantic Aggregation and Adaptive 2D-1D Registration  [paper](https://arxiv.org/pdf/2103.02845v1.pdf)  [code](https://github.com/SeanChenxy/HandMesh)

##### • Model-based 3D Hand Reconstruction via Self-Supervised Learning  [paper](https://arxiv.org/pdf/2103.11703v1.pdf)  [code](https://github.com/TerenceCYJ/S2HAND)

##### • Action-Conditioned 3D Human Motion Synthesis with Transformer VAE  [paper](https://arxiv.org/pdf/2104.05670.pdf)

##### • Semi-Supervised 3D Hand-Object Poses Estimation with Interactions in Time  [paper](https://arxiv.org/pdf/2106.05266v1.pdf)

##### • RGB2Hands: Real-Time Tracking of 3D Hand Interactions from Monocular RGB Video  [paper](https://arxiv.org/pdf/2106.11589v1.pdf)

##### • ArtiBoost: Boosting Articulated 3D Hand-Object Pose Estimation via Online Exploration and Synthesis  [paper](https://arxiv.org/pdf/2109.05488v1.pdf)  [code](https://github.com/MVIG-SJTU/ArtiBoost)

##### • Monocular 3D Reconstruction of Interacting Hands via Collision-Aware Factorized Refinements  [paper](https://arxiv.org/pdf/2111.00763v1.pdf)  [code](https://penincillin.github.io/ihmr_3dv2021)

##### • Dynamic Iterative Refinement for Efficient 3D Hand Pose Estimation  [paper](https://arxiv.org/pdf/2111.06500v1.pdf)

##### • Semi-Supervised 3D Hand Shape and Pose Estimation with Label Propagation  [paper](https://arxiv.org/pdf/2111.15199v1.pdf)

##### • MobRecon: Mobile-Friendly Hand Mesh Reconstruction from Monocular Image  [paper](https://arxiv.org/pdf/2112.02753v1.pdf)  [code](https://github.com/SeanChenxy/HandMesh)

##### • Consistent 3D Hand Reconstruction in Video via Self-Supervised Learning  [paper](https://arxiv.org/pdf/2201.09548v1.pdf)

##### • Interacting Attention Graph for Single Image Two-Hand Reconstruction  [paper](https://arxiv.org/pdf/2203.09364v1.pdf)

##### • HandOccNet: Occlusion-Robust 3D Hand Mesh Estimation Network  [paper](https://arxiv.org/abs/2203.14564)  [code](https://github.com/namepllet/HandOccNet)

##### • TOCH: Spatio-Temporal Object Correspondence to Hand for Motion Refinement  [paper](https://arxiv.org/pdf/2205.07982v1.pdf)

##### • End-to-End 3D Hand Pose Estimation from Stereo Cameras  [paper](https://arxiv.org/pdf/2206.01384v1.pdf)

##### • Efficient Annotation and Learning for 3DHand Pose Estimation: A Survey  [paper](https://arxiv.org/pdf/2206.02257v1.pdf)

##### • 3D Interacting Hand Pose Estimation by Hand De-occlusion and Removal  [code](https://github.com/MengHao666/HDR)

### 3d_cloth

##### • REC-MV: REconstructing 3D Dynamic Cloth from Monucular Videos  [github](https://github.com/GAP-LAB-CUHK-SZ/REC-MV)

### 3d_hair

##### • NeuralHDHair: Automatic High-fidelity Hair Modeling from a Single Image Using Implicit Neural Representations  [paper](https://arxiv.org/pdf/2205.04175v1.pdf)  [code](https://github.com/KeyuWu-CS/NeuralHDHair)

##### •3D hair synthesis using volumetric variational autoencoders

##### •AO-CNN: filament-aware hair reconstruction based on volumetric vector fields

##### •Neural Strands: Learning Hair Geometry and Appearance from Multi-View Images  [paper](https://arxiv.org/abs/2207.14067)

##### •HairStep: Transfer Synthetic to Real Using Strand and Depth Maps for Single-View 3D Hair Modeling  [paper](https://arxiv.org/pdf/2303.02700.pdf)  [code](https://github.com/GAP-LAB-CUHK-SZ/HairStep)

##### • MonoHair: High-Fidelity Hair Modeling from a Monocular Video [code]https://github.com/KeyuWu-CS/MonoHair

### 3d_teeth

##### • Model-based teeth reconstruction  [paper](https://vcai.mpi-inf.mpg.de/projects/MZ/Papers/SGASIA2016_TR/page.html)

##### • An Implicit Parametric Morphable Dental Model  [project](https://vcai.mpi-inf.mpg.de/projects/DMM/)

### 3d_eyelids

##### • Real-time 3D Eyelids Tracking from Semantic Edges  [paper](http://xufeng.site/publications/2017/2017_Real-time%203D%20Eyelids%20Tracking%20from%20Semantic%20Edges-min.pdf)

### 3d foot

##### • FIND: An Unsupervised Implicit 3D Model of Articulated Human Feet [project](https://ollieboyne.github.io/FIND/)

## related

### human_mattting

##### • Real-Time High-Resolution Background Matting  [code](https://github.com/PeterL1n/BackgroundMattingV2)

##### • Real-Time Monocular Human Depth Estimation and Segmentation on Embedded Systems  [paper](https://arxiv.org/pdf/2108.10506v1.pdf)

##### • DeepSportLab: a Unified Framework for Ball Detection, Player Instance Segmentation and Pose Estimation in Team Sports Scenes  [paper](https://arxiv.org/pdf/2112.00627v1.pdf)

##### • PP-HumanSeg: Connectivity-Aware Portrait Segmentation with a Large-Scale Teleconferencing Video Dataset  [paper](https://arxiv.org/pdf/2112.07146v1.pdf)  [code](https://github.com/PaddlePaddle/PaddleSeg)

##### • Portrait Segmentation Using Deep Learning  [paper](https://arxiv.org/pdf/2202.02705v1.pdf)

##### • Human Instance Matting via Mutual Guidance and Multi-Instance Refinement  [paper](https://arxiv.org/pdf/2205.10767v1.pdf)  [code](https://github.com/nowsyn/InstMatt)

##### • 3DHumanGAN: Towards Photo-Realistic 3D-Aware Human Image Generation  [paper](http://aixpaper.com/view/3dhumangan_towards_photorealistic_3daware_human_image_generation)  [code](https://github.com/3dhumangan/3DHumanGAN)

##### • Test-time Adaptation vs. Training-time Generalization: A Case Study in Human Instance Segmentation using Keypoints Estimation  [paper](https://arxiv.org/pdf/2212.06242v1.pdf)

##### • Body Segmentation Using Multi-task Learning  [paper](https://arxiv.org/pdf/2212.06550v1.pdf)

### pose_estimation

##### • CanonPose: Self-Supervised Monocular 3D Human Pose Estimation in the Wild  [paper](https://arxiv.org/pdf/2011.14679.pdf)

##### • Active Learning for Bayesian 3D Hand Pose Estimation  [paper](https://arxiv.org/pdf/2010.00694v2.pdf)  [code](https://github.com/razvancaramalau/al_bhpe)

##### • A-NeRF: Surface-free Human 3D Pose Refinement via Neural Rendering

##### • HandsFormer: Keypoint Transformer for Monocular 3D Pose Estimation of Hands and Object in Interaction  [paper](https://arxiv.org/pdf/2104.14639v1.pdf)

##### • HuMoR: 3D Human Motion Model for Robust Pose Estimation  [paper](https://geometry.stanford.edu/projects/humor/)

##### • Multi-Person Extreme Motion Prediction with Cross-Interaction Attention  [paper](https://arxiv.org/abs/2105.08825)

##### • VoxelTrack: Multi-Person 3D Human Pose Estimation and Tracking in the Wild  [paper](https://arxiv.org/pdf/2108.02452v1.pdf)

##### • Gravity-Aware Monocular 3D Human-Object Reconstruction  [paper&code](http://4dqv.mpi-inf.mpg.de/GraviCap/)

##### • DensePose 3D: Lifting Canonical Surface Maps of Articulated Objects to the Third Dimension  [paper](https://arxiv.org/pdf/2109.00033v1.pdf)

##### • Graph-Based 3D Multi-Person Pose Estimation Using Multi-View Images  [paper](https://arxiv.org/pdf/2109.05885v1.pdf)

##### • Learning Dynamical Human-Joint Affinity for 3D Pose Estimation in Videos  [paper](https://arxiv.org/pdf/2109.07353v1.pdf)

##### • Physics-based Human Motion Estimation and Synthesis from Videos  [paper](https://arxiv.org/pdf/2109.09913.pdf)

##### • Real-time, low-cost multi-person 3D pose estimation  [paper](https://arxiv.org/pdf/2110.11414v1.pdf)

##### • Direct Multi-view Multi-person 3D Human Pose Estimation  [paper](https://arxiv.org/pdf/2111.04076.pdf)  [code](https://github.com/sail-sg/mvp)

##### • Rethinking Keypoint Representations: Modeling Keypoints and Poses as Objects for Multi-Person Human Pose Estimation  [code](https://github.com/wmcnally/kapao)

##### • Camera Distortion-aware 3D Human Pose Estimation in Video with Optimization-based Meta-Learning  [paper](https://arxiv.org/pdf/2111.15056v1.pdf)  [code](https://github.com/hanbyel0105/CamDistHumanPose3D)

##### • In-Bed Human Pose Estimation from Unseen and Privacy-Preserving Image Domains  [paper](https://arxiv.org/pdf/2111.15124v1.pdf)

##### • Camera Motion Agnostic 3D Human Pose Estimation  [paper](https://github.com/seonghyunkim1212/GMR)  [code](https://arxiv.org/pdf/2112.00343v1.pdf)

##### • ElePose: Unsupervised 3D Human Pose Estimation by Predicting Camera Elevation and Learning Normalizing Flows on 2D Poses  [paper](https://arxiv.org/pdf/2112.07088v1.pdf)

##### • Multi-modal 3D Human Pose Estimation with 2D Weak Supervision in Autonomous Driving  [paper](https://arxiv.org/pdf/2112.12141v1.pdf)

##### • AdaptPose: Cross-Dataset Adaptation for 3D Human Pose Estimation by Learnable Motion Generation  [paper](https://arxiv.org/pdf/2112.11593v1.pdf)

##### • FLAG: Flow-based 3D Avatar Generation from Sparse Observations  [paper](https://arxiv.org/pdf/2203.05789v1.pdf)

##### • Pose-MUM : Reinforcing Key Points Relationship for Semi-Supervised Human Pose Estimation  [paper]()

##### • Distribution-Aware Single-Stage Models for Multi-Person 3D Pose Estimation  [paper](https://arxiv.org/pdf/2203.07697v1.pdf)

##### • P-STMO: Pre-Trained Spatial Temporal Many-to-One Model for 3D Human Pose Estimation  [paper](https://arxiv.org/pdf/2203.07628v1.pdf)  [code](https://github.com/paTRICK-swk/P-STMO)

##### • PosePipe: Open-Source Human Pose Estimation Pipeline for Clinical Research  [paper](https://arxiv.org/pdf/2203.08792v1.pdf)  [code](https://github.com/peabody124/PosePipeline/)

##### • 3D Human Pose Estimation Using Möbius Graph Convolutional Networks  [paper](https://arxiv.org/pdf/2203.10554v1.pdf)

##### • Ray3D: ray-based 3D human pose estimation for monocular absolute 3D localization  [paper](https://arxiv.org/pdf/2203.11471v1.pdf)  [code](https://github.com/YxZhxn/Ray3D)

##### • YOLO-Pose: Enhancing YOLO for Multi Person Pose Estimation Using Object Keypoint Similarity Loss [paper](https://arxiv.org/pdf/2204.06806v1.pdf)  [code](https://github.com/TexasInstruments/edgeai-yolov5)

##### • Permutation-Invariant Relational Network for Multi-person 3D Pose Estimation  [paper](https://arxiv.org/pdf/2204.04913v1.pdf)

##### • Non-Local Latent Relation Distillation for Self-Adaptive 3D Human Pose Estimation  [paper](https://arxiv.org/pdf/2204.01971v1.pdf)

##### • Aligning Silhouette Topology for Self-Adaptive 3D Human Pose Recovery  [paper](https://arxiv.org/pdf/2204.01276v1.pdf)

##### • Dite-HRNet: Dynamic Lightweight High-Resolution Network for Human Pose Estimation  [paper](https://arxiv.org/pdf/2204.10762v1.pdf)

##### • PedRecNet: Multi-task deep neural network for full 3D human pose and orientation estimation  [paper](https://arxiv.org/pdf/2204.11548v1.pdf)

##### • "Teaching Independent Parts Separately" (TIPS-GAN) : Improving Accuracy and Stability in Unsupervised Adversarial 2D to 3D Human Pose Estimation  [paper](https://arxiv.org/pdf/2205.05980v1.pdf)

##### •Lightweight Human Pose Estimation Using Heatmap-Weighting Loss  [paper](https://arxiv.org/pdf/2205.10611v1.pdf)

##### •VTP: Volumetric Transformer for Multi-view Multi-person 3D Pose Estimation  [paper](https://arxiv.org/pdf/2205.12602v1.pdf)

##### •Location-free Human Pose Estimation  [paper](https://arxiv.org/pdf/2205.12619v1.pdf)

##### •Trajectory Optimization for Physics-Based Reconstruction of 3d Human Pose from Monocular Video  [paper](https://arxiv.org/pdf/2205.12292v1.pdf)

##### •SPGNet: Spatial Projection Guided 3D Human Pose Estimation in Low Dimensional Space  [paper](https://arxiv.org/pdf/2206.01867v1.pdf)

##### •GraphMLP: A Graph MLP-Like Architecture for 3D Human Pose Estimation  [paper](https://arxiv.org/pdf/2206.06420v1.pdf)

##### •BlazePose GHUM Holistic: Real-time 3D Human Landmarks and Pose Estimation  [paper](https://arxiv.org/pdf/2206.11678v1.pdf)

##### •Mutual Adaptive Reasoning for Monocular 3D Multi-Person Pose Estimation  [paper](https://arxiv.org/pdf/2207.07900v1.pdf)

##### •Human keypoint detection for close proximity human-robot interaction  [paper](https://arxiv.org/pdf/2207.07742v1.pdf)

##### •VirtualPose: Learning Generalizable 3D Human Pose Models from Virtual Data  [paper](https://arxiv.org/pdf/2207.09949v1.pdf)

##### •3D Clothed Human Reconstruction in the Wild  [paper](https://arxiv.org/pdf/2207.10053v1.pdf)  [code](https://github.com/hygenie1228/ClothWild_RELEASE)

##### •EFFICIENT AND ACCURATE SKELETON-BASED TWO-PERSON INTERACTION RECOGNITION USING INTER- AND INTRA-BODY GRAPHS  [paper](https://arxiv.org/pdf/2207.12648v1.pdf)

##### •Learning to Estimate 3D Human Pose from Point Cloud  [paper](https://arxiv.org/pdf/2212.12910v1.pdf)

##### •Scene-aware Egocentric 3D Human Pose Estimation  [paper](https://arxiv.org/pdf/2212.11684v1.pdf)

##### •Advanced Baseline for 3D Human Pose Estimation: A Two-Stage Approach  [paper](https://arxiv.org/pdf/2212.11344v1.pdf)

##### •GFPose: Learning 3D Human Pose Prior with Gradient Fields  [paper](https://arxiv.org/pdf/2212.08641v1.pdf)

##### •HUM3DIL: Semi-supervised Multi-modal 3D Human Pose Estimation for Autonomous Driving  [paper](https://arxiv.org/pdf/2212.07729v1.pdf)

##### •TOWARDS SINGLE CAMERA HUMAN 3D-KINEMATICS  [paper](https://arxiv.org/pdf/2301.05435v1.pdf)

##### •Markerless Body Motion Capturing for 3D Character Animation based on Multi-view Cameras  [paper](https://arxiv.org/pdf/2212.05788v1.pdf)

##### •DiffuPose: Monocular 3D Human Pose Estimation via Denoising Diffusion Probabilistic Model  [paper](https://arxiv.org/pdf/2212.02796v1.pdf)

##### •2D Human Pose Estimation with Explicit Anatomical Keypoints Structure Constraints  [paper](https://arxiv.org/pdf/2212.02163v1.pdf)

##### •Weakly Supervised 3D Multi-person Pose Estimation for Large-scale Scenes based on Monocular Camera and Single LiDAR  [paper](https://arxiv.org/pdf/2211.16951v1.pdf)

##### •Kinematic-aware Hierarchical Attention Network for Human Pose Estimation in Videos  [paper](https://github.com/KyungMinJin/HANet)  [code](https://github.com/KyungMinJin/HANet)

##### •Proactive Multi-Camera Collaboration for 3D Human Pose Estimation  [homepage](https://sites.google.com/view/active3dpose)

### registration

##### • LoopReg: Self-supervised Learning of Implicit Surface Correspondences, Pose and Shape for 3D Human Mesh Registration  [paper](https://virtualhumans.mpi-inf.mpg.de/papers/bhatnagar2020loopreg/bhatnagar2020loopreg.pdf)  [code](https://github.com/bharat-b7/LoopReg)

##### • Neural Deformation Graphs for Globally-consistent Non-rigid Reconstruction  [paper](https://arxiv.org/pdf/2012.01451.pdf) [code](https://github.com/AljazBozic/NeuralGraph)

##### • FARM: Functional Automatic Registration Method for 3D Human Bodies  [paper](https://arxiv.org/abs/1807.10517)  [code](https://github.com/riccardomarin/FARM)

##### • Locally Aware Piecewise Transformation Fields for 3D Human Mesh Registration  [paper](https://arxiv.org/pdf/2104.08160v1.pdf)

##### • Unsupervised 3D Human Mesh Recovery from Noisy Point Clouds  [paper](https://arxiv.org/pdf/2107.07539v1.pdf)

### correspondence

##### • HumanGPS: Geodesic PreServing Feature for Dense Human Correspondences  [paper](https://feitongt.github.io/HumanGPS/paper.pdf)

##### •BodyMap: Learning Full-Body Dense Correspondence Map  [paper](https://arxiv.org/pdf/2205.09111v1.pdf)

##### •CorrI2P: Deep Image-to-Point Cloud Registration via Dense Correspondence  [paper](https://arxiv.org/pdf/2207.05483v1.pdf)

### application

##### • One-Shot Free-View Neural Talking-Head Synthesis for Video Conferencing  [paper](https://arxiv.org/pdf/2011.15126.pdf)

##### • LipSync3D: Data-Efficient Learning of Personalized 3D Talking Faces from Video using Pose and Lighting Normalization  [paper](https://arxiv.org/pdf/2106.04185v1.pdf)

##### • ARShoe: Real-Time Augmented Reality Shoe Try-on System on Smartphones  [paper](https://arxiv.org/pdf/2108.10515v1.pdf)

##### • A Neural Anthropometer Learning from Body Dimensions Computed on Human 3D Meshes  [paper](https://arxiv.org/pdf/2110.04064v1.pdf)

##### • Robust 3D Garment Digitization from Monocular 2D Images for 3D Virtual Try-On Systems  [paper](https://arxiv.org/pdf/2111.15140v1.pdf)

##### • Single-image Human-body Reshaping with Deep Neural Networks  [paper](https://arxiv.org/pdf/2203.10496v1.pdf)

##### • Style-Based Global Appearance Flow for Virtual Try-On  [paper](https://arxiv.org/pdf/2204.01046v1.pdf)

##### • Monitoring of Pigmented Skin Lesions Using 3D Whole Body Imaging  [paper](https://arxiv.org/pdf/2205.07085v1.pdf)

##### • ESTIMATION OF 3D BODY SHAPE AND CLOTHING MEASUREMENTS FROM FRONTALAND SIDE-VIEW IMAGES  [paper](https://arxiv.org/pdf/2205.14347v1.pdf)

##### • Dressing Avatars: Deep Photorealistic Appearance for Physically Simulated Clothing  [paper](https://arxiv.org/pdf/2206.15470.pdf)

##### • AIFit: Automatic 3D Human-Interpretable Feedback Models for Fitness Training  [paper](http://vision.imar.ro/fit3d/)

### texture 

##### • Spatiotemporal Texture Reconstruction for Dynamic Objects Using a Single RGB-D Camera  [paper](https://arxiv.org/pdf/2108.09007v1.pdf)

##### • Semi-supervised Synthesis of High-Resolution Editable Textures for 3D Humans  [paper](https://openaccess.thecvf.com/content/CVPR2021/papers/Chaudhuri_Semi-Supervised_Synthesis_of_High-Resolution_Editable_Textures_for_3D_Humans_CVPR_2021_paper.pdf)

##### • StylePeople: A Generative Model of Fullbody Human Avatars  [paper](https://arxiv.org/pdf/2104.08363.pdf)  [code](https://github.com/saic-vul/style-people)

##### • Refining 3D Human Texture Estimation from a Single Image  [paper](https://arxiv.org/pdf/2303.03471v1.pdf)

### skin

##### • HeterSkinNet: A Heterogeneous Network for Skin Weights Prediction  [paper](https://arxiv.org/pdf/2103.10602.pdf)

##### • SNARF: Differentiable Forward Skinning for Animating Non-Rigid Neural Implicit Shapes  [paper](https://arxiv.org/pdf/2104.03953.pdf)

### lighting

##### • Relighting Humans in the Wild: Monocular Full-Body Human Relighting with Domain Adaptation  [code](https://github.com/majita06/Relighting_in_the_Wild)

### talking_head

##### • DisCoHead: Audio-and-Video-Driven Talking Head Generation by Disentangled Control of Head Pose and Facial Expressions  [code](https://github.com/deepbrainai-research/discohead)

##### • Imitator: Personalized Speech-driven 3D Facial Animation  [homepage](https://zielon.github.io/insta/)

##### • EmoTalk: Speech-driven emotional disentanglement for 3D face animation  [homepage](https://ziqiaopeng.github.io/emotalk/)

### uncategorized

##### • Fully Convolutional Graph Neural Networks for Parametric Virtual Try-On  [paper](https://arxiv.org/pdf/2009.04592.pdf)

##### • TailorNet: Predicting Clothing in 3D as a Function of Human Pose, Shape and Garment Style  [paper](https://arxiv.org/abs/2003.04583)  [code](https://github.com/chaitanya100100/TailorNet)

##### • 3DBooSTeR: 3D Body Shape and Texture Recovery  [paper](https://arxiv.org/pdf/2010.12670.pdf)

##### • Neural 3D Clothes Retargeting from a Single Image  [paper](https://arxiv.org/pdf/2102.00062v1.pdf)

##### • Single-image Full-body Human Relighting  [paper](https://arxiv.org/pdf/2107.07259.pdf)

##### • iButter: Neural Interactive Bullet Time Generator for Human Free-viewpoint Rendering  [paper](https://arxiv.org/pdf/2108.05577.pdf)

##### • A Riemannian Framework for Analysis of Human Body Surface  [paper](https://arxiv.org/pdf/2108.11449v1.pdf)

##### • The Power of Points for Modeling Humans in Clothing  [paper&code](https://qianlim.github.io/POP.html)

##### • Neural Human Deformation Transfer  [paper](https://arxiv.org/pdf/2109.01588v1.pdf)

##### • 3D Human Texture Estimation from a Single Image with Transformers  [paper](https://arxiv.org/pdf/2109.02563v1.pdf)

##### • Learning to Predict Diverse Human Motions from a Single Image via Mixture Density Networks  [paper](https://arxiv.org/pdf/2109.05776v1.pdf)

##### • ZFlow: Gated Appearance Flow-based Virtual Try-on with 3D Priors  [paper](https://arxiv.org/pdf/2109.07001v1.pdf)

##### • A Shading-Guided Generative Implicit Model for Shape-Accurate 3D-Aware Image Synthesis  [paper](https://arxiv.org/abs/2110.15678)  [code](https://github.com/XingangPan/ShadeGAN)

##### • Action2video: Generating Videos of Human 3D Actions  [paper](https://arxiv.org/pdf/2111.06925v1.pdf)

##### • Garment4D: Garment Reconstruction from Point Cloud Sequences  [paper](https://papers.nips.cc/paper/2021/file/eb160de1de89d9058fcb0b968dbbbd68-Paper.pdf)  [code](https://github.com/hongfz16/Garment4D)

##### • ADG-Pose: Automated Dataset Generation for Real-World Human Pose Estimation  [paper](https://arxiv.org/pdf/2202.00753v1.pdf)  [code](https://github.com/TeCSAR-UNCC/ADG-Pose)

##### • DiffusionNet: Discretization Agnostic Learning on Surfaces  [paper](https://arxiv.org/pdf/2012.00888.pdf)

##### • Text and Image Guided 3D Avatar Generation and Manipulation  [paper](https://arxiv.org/pdf/2202.06079v1.pdf)  [code](https://catlab-team.github.io/)

##### • Quantification of Occlusion Handling Capability of a 3D Human Pose Estimation Framework  [paper](https://arxiv.org/pdf/2203.04113v1.pdf)

##### • Motron: Multimodal Probabilistic Human Motion Forecasting  [paper](https://arxiv.org/pdf/2203.04132v1.pdf)

##### • FEXGAN-META: FACIAL EXPRESSION GENERATION WITH META HUMANS  [paper](https://arxiv.org/pdf/2203.05975v1.pdf)

##### • ActFormer: A GAN Transformer Framework towards General Action-Conditioned 3D Human Motion Generation

##### • Domain Adaptive Hand Keypoint and Pixel Localization in the Wild  [paper](https://arxiv.org/pdf/2203.08344v1.pdf)

##### • Portrait Eyeglasses and Shadow Removal by Leveraging 3D Synthetic Data  [paper](https://arxiv.org/pdf/2203.10474v1.pdf)

##### • Recognition of Freely Selected Keypoints on Human Limbs  [paper](https://arxiv.org/pdf/2204.06326v1.pdf)

##### • What’s in your hands? 3D Reconstruction of Generic Objects in Hands  [paper](https://arxiv.org/pdf/2204.07153v1.pdf)  [code](https://github.com/JudyYe/ihoi)

##### • CHORE: Contact, Human and Object REconstruction from a single RGB image  [paper](https://arxiv.org/pdf/2204.02445v1.pdf)

##### • SNUG: Self-Supervised Neural Dynamic Garments  [paper](https://arxiv.org/pdf/2204.02219v1.pdf)

##### • 3D Magic Mirror: Clothing Reconstruction from a Single Image via a Causal Perspective  [paper](https://arxiv.org/pdf/2204.13096v1.pdf)

##### • Fake it till you make it: face analysis in the wild using synthetic data alone  [homepage](https://microsoft.github.io/FaceSynthetics/)

##### • AvatarCLIP: Zero-Shot Text-Driven Generation and Animation of 3D Avatars  [paper](https://arxiv.org/pdf/2205.08535v1.pdf)  [code](https://github.com/hongfz16/AvatarCLIP)

##### • Scene Aware Person Image Generation through Global Contextual Conditioning  [paper](https://arxiv.org/pdf/2206.02717v1.pdf)

##### • HairFIT: Pose-Invariant Hairstyle Transfer via Flow-based Hair Alignment and Semantic-Region-Aware Inpainting  [paper](https://arxiv.org/pdf/2206.08585v1.pdf)

##### • From a few Accurate 2D Correspondences to 3D Point Clouds  [paper](https://arxiv.org/pdf/2206.08749v1.pdf)

##### • Convolutional Neural Network Based Partial Face Detection  [paper](https://arxiv.org/pdf/2206.14350v1.pdf)

##### • SPSN: Superpixel Prototype Sampling Network for RGB-D Salient Object Detection  [paper](https://arxiv.org/pdf/2207.07898v1.pdf)  [code](https://github.com/Hydragon516/SPSN)

##### • Detecting Humans in RGB-D Data with CNNs  [paper](https://arxiv.org/pdf/2207.08064v1.pdf)

##### • Animation from Blur: Multi-modal Blur Decomposition with Motion Guidance  [paper](https://arxiv.org/pdf/2207.10123.pdf)

##### • 3D Shape Sequence of Human Comparison and Classification using Current and Varifolds  [paper](https://arxiv.org/pdf/2207.12485v1.pdf)  [code](https://github.com/CRISTAL-3DSAM/HumanComparisonVarifolds)

##### • KinePose: A temporally optimized inverse kinematics technique for 6DOF human pose estimation with biomechanical constraints  [paper](https://arxiv.org/pdf/2207.12841v1.pdf)  [code](https://github.com/KevGildea/KinePose)

##### • Skeleton-free Pose Transfer for Stylized 3D Character  [paper](https://www.arxiv-vanity.com/papers/2208.00790/?continueFlag=acd9680585ca1db48ed3cbc277e4da97)

##### • Learning Continuous Mesh Representation with Spherical Implicit Surface  [paper](https://arxiv.org/pdf/2301.04695v1.pdf)

##### • Scene Synthesis from Human Motion  [paper](https://arxiv.org/pdf/2301.01424v1.pdf)

##### • Ego-Body Pose Estimation via Ego-Head Pose Estimation  [paper](https://arxiv.org/pdf/2212.04636v1.pdf)

##### • Physically Plausible Animation of Human Upper Body from a Single Image  [paper](https://arxiv.org/pdf/2212.04741v1.pdf)

## parametric model

### body

##### • SMPL: A Skinned Multi-Person Linear Model  [paper](https://files.is.tue.mpg.de/black/papers/SMPL2015.pdf)  [code](https://github.com/CalciferZh/SMPL)

##### • Expressive Body Capture: 3D Hands, Face, and Body from a Single Image  [paper](https://arxiv.org/abs/1904.05866)  [code](https://github.com/vchoutas/smplx)

##### • STAR: Sparse Trained Articulated Human Body Regressor  [paper](https://arxiv.org/abs/2008.08535)  [code](https://github.com/ahmedosman/STAR)

### face

##### • Basel Face Model 2009  [website](http://faces.cs.unibas.ch/bfm/?nav=1-0&id=basel_face_model)

##### • Basel Face Model 2017  [website](http://faces.cs.unibas.ch/bfm/bfm2017.html)

##### • Large Scale 3D Morphable Model  [website](https://xip.uclb.com/i/healthcare_tools/LSFM.html)

##### • A Morphable Face Albedo Model  [github](https://github.com/waps101/AlbedoMM)

##### • Learning a 3D Morphable Face Reflectance Model from Low-cost Data  [paper](https://arxiv.org/pdf/2303.11686.pdf)  [code](https://github.com/yxuhan/ReflectanceMM)

### head

##### • FLAME: Articulated Expressive Head Model  [website](http://flame.is.tue.mpg.de/)

### hand

##### • MANO  [paper](https://ps.is.mpg.de/uploads_file/attachment/attachment/392/Embodied_Hands_SiggraphAsia2017.pdf)  [website](https://mano.is.tue.mpg.de/)

##### • NIMBLE: A Non-rigid Hand Model with Bones and Muscles  [paper](https://arxiv.org/pdf/2202.04533v1.pdf)

### method

##### •GHUM & GHUML: Generative 3D Human Shape and Articulated Pose Models  [github](https://github.com/google-research/google-research/tree/master/ghum)

##### •Large Scale 3D Morphable Models  [paper](https://link.springer.com/article/10.1007/s11263-017-1009-7)  [code](https://github.com/menpo/lsfm)

##### •Morphable Face Models - An Open Framework  [paper](https://arxiv.org/abs/1709.08398)  [code](https://github.com/unibas-gravis/basel-face-pipeline)

## dataset

### face

##### • MAAD-Face: A Massively Annotated Attribute Dataset for Face Images  [paper](https://github.com/pterhoer/MAAD-Face)

##### • FaceScape: 3D Facial Dataset and Benchmark for Single-View 3D Face Reconstruction  [paper](https://arxiv.org/pdf/2111.01082v1.pdf)

##### • 300W-LP &  AFLW2000-3D  [homepage](http://www.cbsr.ia.ac.cn/users/xiangyuzhu/projects/3DDFA/main.htm)

##### • AFLW  [website](https://www.tugraz.at/institute/icg/research/team-bischof/lrs/downloads/aflw/)

##### • REALY: Rethinking the Evaluation of 3D Face Reconstruction [paper](https://arxiv.org/pdf/2203.09729v1.pdf)  [website](https://www.realy3dface.com/)

##### • FaceVerse-High Quality 3D Face Dataset  [github](https://github.com/LizhenWangT/FaceVerse-Dataset)

##### • DAD-3DHeads: A Large-scale Dense, Accurate and Diverse Dataset for 3D Head Alignment from a Single Image  [paper](https://arxiv.org/pdf/2204.03688v1.pdf)  [github](https://github.com/PinataFarms/DAD-3DHeads)

##### • Multiface: A Dataset for Neural Face Rendering  [paper](https://arxiv.org/pdf/2207.11243.pdf)

##### • DAD-3DHeads: A Large-scale Dense, Accurate and Diverse Dataset for 3D Head Alignment from a Single Image  [paper](https://arxiv.org/abs/2204.03688)

##### • mimicme  [github](https://github.com/apapaion/mimicme)

### hand

##### • GRAB: A Dataset of Whole-Body Human Grasping of Objects  [github](https://github.com/otaheri/GRAB)

##### • Reconstructing Hand-Object Interactions in the Wild  [github](https://github.com/ZheC/MOW)

##### • Ego2HandsPose: A Dataset for Egocentric Two-hand 3D Global Pose Estimation  [paper](https://arxiv.org/pdf/2206.04927v1.pdf)

##### • Interhand2.6M

### body

##### • NTU60-X: TOWARDS SKELETON-BASED RECOGNITION OF SUBTLE HUMAN ACTIONS  [code](https://arxiv.org/pdf/2101.11529.pdf)

##### • AGORA: Avatars in Geography Optimized for Regression Analysis  [homepage](https://agora.is.tue.mpg.de/)

##### • AMASS: Archive of Motion Capture as Surface Shapes  [paper](https://arxiv.org/pdf/1904.03278.pdf)  [github](https://github.com/nghorbani/amass)

##### • ASL-Skeleton3D and ASL-Phono: Two Novel Datasets for the American Sign Language  [paper](https://arxiv.org/pdf/2201.02065v1.pdf)

##### •MPI-INF-3DHP [homepage](https://vcai.mpi-inf.mpg.de/3dhp-dataset/)

##### •Human3.6M  [website](http://vision.imar.ro/human3.6m/description.php)

##### •3DPW  [website](https://virtualhumans.mpi-inf.mpg.de/3DPW/)

##### •PennAction  [website](http://dreamdragon.github.io/PennAction/)

##### •Insta Variety  [github](https://github.com/akanazawa/human_dynamics/blob/master/doc/insta_variety.md)

##### •PoseTrack  [homapage](https://posetrack.net/)

##### •Kinetics-400  [website](https://deepmind.com/research/open-source/kinetics)

##### •RenderPeople  [website](https://renderpeople.com/)

##### •BUFF  [website](https://buff.is.tue.mpg.de/)

##### •People Snapshot Dataset  [homepage](https://graphics.tu-bs.de/people-snapshot)

##### •Multi-Garment  [homepage](https://virtualhumans.mpi-inf.mpg.de/mgn/)

##### •iPER [website](https://svip-lab.github.io/dataset/iPER_dataset.html)

##### •ZJU-MoCap  [homepage](https://chingswy.github.io/Dataset-Demo/)

##### •SmartPortraits: Depth Powered Handheld Smartphone Dataset of Human Portraits for State Estimation, Reconstruction and Synthesis  [paper](https://arxiv.org/pdf/2204.10211v1.pdf)

##### •MVP-Human Dataset for 3D Human Avatar Reconstruction from Unconstrained Frames  [paper](https://arxiv.org/pdf/2204.11184v1.pdf)

##### •HuMMan: Multi-Modal 4D Human Dataset for Versatile Sensing and Modeling  [paper](https://arxiv.org/pdf/2204.13686v1.pdf) [github](https://github.com/caizhongang/humman_toolbox)

##### •3DMPB-dataset  [github](https://github.com/boycehbz/3DMPB-dataset)

##### •imar_vision_datasets_tools  [github](https://github.com/sminchisescu-research/imar_vision_datasets_tools)

##### •RICH: Real scenes, Interaction, Contacts and Humans [github](https://github.com/paulchhuang/rich_toolkit)

##### •Cloth3d [github](https://github.com/hbertiche/CLOTH3D)

##### •DDH-QA  [arxiv](https://arxiv.org/pdf/2212.12734v1.pdf)

##### •H3WB: Human3.6M 3D WholeBody Dataset and Benchmark  [github](https://github.com/wholebody3d/wholebody3d)

##### •LightStage  [homepage](https://chingswy.github.io/Dataset-Demo/)

### whole body

##### •Motion-X  [homepage](https://motion-x-dataset.github.io/)

### foot

##### •FIND: An Unsupervised Implicit 3D Model of Articulated Human Feet [github](https://github.com/OllieBoyne/Foot3D)

### method

##### •NeuralAnnot: Neural Annotator for 3D Human Mesh Training Sets  [paper](https://arxiv.org/pdf/2011.11232.pdf)

### others

##### • K-Hairstyle: A Large-scale Korean hairstyle dataset for virtual hair editing and hairstyle classification  [homepage](https://www.arxiv-vanity.com/papers/2102.06288/)

##### • Simulated garment dataset for virtual try-on  [address](https://github.com/isantesteban/vto-dataset)

##### • DeepFashion  [homepage](https://liuziwei7.github.io/projects/DeepFashion.html)

##### • Delving into High-Quality Synthetic Face Occlusion Segmentation Datasets  [paper](https://arxiv.org/pdf/2205.06218v1.pdf)

##### • 3A-GAN: Facial Flow for Face Animation with Generative Adversarial Networks  [paper](https://arxiv.org/pdf/2205.06204v1.pdf)

##### • Scanned Objects by Google Research  [website](https://ai.googleblog.com/2022/06/scanned-objects-by-google-research.html?continueFlag=69eb10990d1859f21dd21d22d96e2b22)

##### • EasyPortrait - Face Parsing and Portrait Segmentation Dataset  [github](https://anonymous.4open.science/r/anonymous-dataset-pep8/README.md)

## labs

##### • max planck institute  [website](https://ps.is.tuebingen.mpg.de/publications)

##### • Yebin Liu  [website](http://www.liuyebin.com/)

##### • ZJU3DV  [github](https://github.com/zju3dv)

##### • Hujun Bao  [google scholar](https://scholar.google.com/citations?hl=zh-CN&user=AZCcDmsAAAAJ&view_op=list_works&sortby=pubdate)

##### • USTC-3DV  [homepage](http://staff.ustc.edu.cn/~juyong/index.html)

##### • Hao_Li [homepage](http://www.hao-li.com/Hao_Li/Hao_Li_-_about_me.html)

## other related awesome

##### • awesome-clothed-human  [github](https://github.com/weihaox/awesome-clothed-human)

##### • curated-list-of-awesome-3D-Morphable-Model-software-and-data  [github](https://github.com/3d-morphable-models/curated-list-of-awesome-3D-Morphable-Model-software-and-data)

##### • awesome-hand-pose-estimation  [github](https://github.com/xinghaochen/awesome-hand-pose-estimation)

##### • Awesome 3D Body Papers  [github](https://github.com/3DFaceBody/awesome-3dbody-papers)

##### • Body_Reconstruction_References  [github](https://github.com/chenweikai/Body_Reconstruction_References#data-and-code)

##### • 3D-face-reconstruction-paper-list  [github](https://github.com/czh-98/3D-face-reconstruction-paper-list)

##### • awesome_talking_face_generation  [github](https://github.com/YunjinPark/awesome_talking_face_generation)

##### • CG&3DV Twitter  [github](https://github.com/USTC3DV/Truck_of_Twitter_Messages)

##### • FLAME-Universe [github](https://github.com/TimoBolkart/FLAME-Universe)

##### • human-motion-capture  [github](https://github.com/visonpon/human-motion-capture)

## survey

##### • Recovering 3D Human Mesh from Monocular Images: A Survey  [paper](https://arxiv.org/pdf/2203.01923v1.pdf)  [github](https://github.com/tinatiansjz/hmr-survey)

##### • 2D Human Pose Estimation: A Survey  [paper](https://arxiv.org/pdf/2204.07370v1.pdf)

##### • A Survey of Non-Rigid 3D Registration  [paper](https://arxiv.org/pdf/2203.07858v1.pdf)

##### • 3D Face Reconstruction in Deep Learning Era: A Survey  [paper](https://link.springer.com/article/10.1007/s11831-021-09705-4)

##### • Towards efficient and photorealistic 3D human reconstruction: A brief survey  [paper](https://www.sciencedirect.com/science/article/pii/S2468502X21000413)

##### • Survey on 3D face reconstruction from uncalibrated images  [paper](https://arxiv.org/abs/2011.05740)

##### • State of the Art on 3D Reconstruction with RGB-D Cameras  [paper](https://zollhoefer.com/papers/EG18_RecoSTAR/paper.pdf)

##### • Awesome-AIGC-3D  [github](https://github.com/hitcslj/Awesome-AIGC-3D.git)

##### • Awesome Digital Human  [github](https://github.com/weihaox/awesome-digital-human.git)

##### • Awesome-AIGC-3D [github](https://github.com/hitcslj/Awesome-AIGC-3D.git)