Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

https://github.com/chenweikai/Body_Reconstruction_References

Paper, dataset and code collection on human body reconstruction
https://github.com/chenweikai/Body_Reconstruction_References

code dataset human-body-reconstruction paper

Last synced: 2 months ago
JSON representation

Paper, dataset and code collection on human body reconstruction

Lists

README 

        
# Human Body Reconstruction 



There are tremendous amount of papers on human body digitization in recent years. 

Below shows my collection of papers organized in a reverse-chronological order. 



## Contents



1. [Multi-view Reconstruction](#Multi-view-Reconstruction)

   - [Deep Learning](#Deep-Learning)

   - [Shape from Silhouette](#Silhouette)

   - [Multi-view Stereo](#Multi-view-Stereo)

   - [Photometric Stereo](#Photometric)

   - [Template based Approaches](#Template)

   - [Parametric Models](#Parametric)

2. [Single-view Reconstruction](#Single-view-Reconstruction)

3. [4D Scans](#4D-Scans)

4. [Dataset and Code](#data-and-code)



## Multi-view Reconstruction






### 1. Deep Learning 



[ICCV19] Shape-Aware Human Pose and Shape Reconstruction Using Multi-View Images [[pdf]](http://openaccess.thecvf.com/content_ICCV_2019/papers/Liang_Shape-Aware_Human_Pose_and_Shape_Reconstruction_Using_Multi-View_Images_ICCV_2019_paper.pdf)



[ICCV19] TexturePose: Supervising Human Mesh Estimation with Texture Consistency [[pdf]](https://www.seas.upenn.edu/~nkolot/files/texturepose.pdf)



[ICCV19] Human Mesh Recovery From Monocular Images via a Skeleton-Disentangled Representation [[pdf]](http://openaccess.thecvf.com/content_ICCV_2019/papers/Sun_Human_Mesh_Recovery_From_Monocular_Images_via_a_Skeleton-Disentangled_Representation_ICCV_2019_paper.pdf)



[ECCV18] Deep Volumetric Video From Very Sparse Multi-View Performance Capture [[pdf]](http://chenweikai.github.io/papers/[ECCV18]Deep%20Volumetric%20Video%20From%20Very%20Sparse%20Multi-View%20Performance%20Capture.pdf)



[ECCV18] Bodynet: Volumetric inference of 3d human body shapes [[pdf]](http://openaccess.thecvf.com/content_ECCV_2018/papers/Gul_Varol_BodyNet_Volumetric_Inference_ECCV_2018_paper.pdf)



[ECCV18] Volumetric performance capture from minimal camera viewpoints [[pdf]](http://openaccess.thecvf.com/content_ECCV_2018/papers/Andrew_Gilbert_Volumetric_performance_capture_ECCV_2018_paper.pdf)






### 2. Shape from Silhouette



[CGF16] 3d body shapes estimation from dressed-human silhouettes [[pdf]](http://eprints.bournemouth.ac.uk/24967/1/1008_original.pdf)



[ICCV15] Interactive visual hull refinement for specular and transparent object surface reconstruction [[pdf]](https://www.cv-foundation.org/openaccess/content_iccv_2015/papers/Zuo_Interactive_Visual_Hull_ICCV_2015_paper.pdf)



[HPG13] Real-time high-resolution sparse voxelization with application to image-based modeling [[pdf]](http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.645.4940&rep=rep1&type=pdf)



[TOG08] Articulated Mesh Animation from Multi-view Silhouettes [[project page]](http://people.csail.mit.edu/drdaniel/mesh_animation/) [[pdf]](https://homes.cs.washington.edu/~jovan/papers/vlasic-2008-ama.pdf) [[data]](http://people.csail.mit.edu/drdaniel/mesh_animation/#data)



[ECCV06] Carved visual hulls for image-based modeling [[pdf]](https://www.di.ens.fr/willow/pdfs/eccv06b.pdf)



[3DPVT06] Visual shapes of silhouette sets [[pdf]](https://hal.archives-ouvertes.fr/hal-00349020/document/)



[CVIU04] Silhouette and stereo fusion for 3d object modeling [[pdf]](https://carlos-hernandez.org/papers/hernandez_cviu04.pdf)



[CVPR03] Visual hull alignment and refinement across time: A 3d reconstruction algorithm combining shape-from-silhouette with stereo [[pdf]](https://www.cs.cmu.edu/~german/research/CVPR2003/VisualHull/VisualHull.pdf)



[CGIT00] Image-based visual hulls [[project page]](https://people.csail.mit.edu/wojciech/IBVH/index.html)[[pdf]](https://people.csail.mit.edu/wojciech/IBVH/ibvh.pdf)






### 3. Multi-view Stereo



[UIST16] Holoportation: Virtual 3d teleportation in real-time [[project page]](https://www.microsoft.com/en-us/research/project/holoportation-3/) [[pdf]](http://www.cs.toronto.edu/~slwang/holoportation.pdf)



[SIGGRAPH15] High-quality streamable free-viewpoint video [[project page]](http://hhoppe.com/proj/fvv/) [[pdf]](http://hhoppe.com/fvv.pdf)



[TVCG10] A point-cloud-based multiview stereo algorithm for free-viewpoint video [[pdf]](https://dl.acm.org/citation.cfm?id=1749522)



[SIGGRAPH08] Markerless garment capture [[project page]](http://www.cs.ubc.ca/labs/imager/tr/2008/MarkerlessGarmentCapture/)[[pdf]](https://vccimaging.org/Publications/Bradley2008MGC/Bradley2008MGC.pdf)



[CGA07] Surface capture for performance-based animation [[pdf]](https://core.ac.uk/download/pdf/397966.pdf)



[TVC05] Scalable 3d video of dynamic scenes [[pdf]](https://cgl.ethz.ch/Downloads/Publications/Papers/2005/Was05/Was05.pdf)






### 4. Photometric Stereo 



[ICCV11] Shading-based dynamic shape refinement from multi-view video under general illumination [[pdf]](http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.226.8025&rep=rep1&type=pdf)



[SIGGRAPH_Asia09] Dynamic shape capture using multi-view photometric stereo [[project page]](http://gl.ict.usc.edu/Research/dynamicshape/) [[pdf]](https://people.csail.mit.edu/wojciech/MultiviewPhotometricStereo/MultiviewPS.pdf)






### 5. Template based Approaches



[TOG13] On-set performance capture of multiple actors with a stereo camera [[pdf]](https://gvv.mpi-inf.mpg.de/files/SIGGRAPH_ASIA_2013/binocap_high.pdf)



[ECCV12] Full body performance capture under uncontrolled and varying illumination: A shading-based approach [[pdf]](http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.367.354&rep=rep1&type=pdf)



[CVPR11] Markerless motion capture

of interacting characters using multi-view image segmentation [[pdf]](https://pages.iai.uni-bonn.de/gall_juergen/download/jgall_multitrack_cvpr11.pdf)



[SIGGRAPH_Asia10] Video-based reconstruction of animatable human characters [[project page]](http://resources.mpi-inf.mpg.de/perfcap/index_vrhc.html)[[pdf]](https://people.mpi-inf.mpg.de/~theobalt/vrhc.pdf)



[SIGGRAPH08] Performance capture from sparse multi-view video [[project page]](http://resources.mpi-inf.mpg.de/perfcap/)[[pdf]](https://gvv.mpi-inf.mpg.de/files/old_site_files/pcmv_preprint.pdf)



[CVPR09] Motion capture using joint skeleton tracking and surface estimation [[pdf]](https://www.tnt.uni-hannover.de/papers/data/773/773_1.pdf)



[CVPR08] Robust fusion of dynamic shape and normal capture for high-quality reconstruction of time-varying

geometry [[pdf]](https://gvv.mpi-inf.mpg.de/files/old_site_files/cvpr08b.pdf)






### 6. Parametric Models



[ICCV19] Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loop [[pdf]](http://openaccess.thecvf.com/content_ICCV_2019/papers/Kolotouros_Learning_to_Reconstruct_3D_Human_Pose_and_Shape_via_Model-Fitting_ICCV_2019_paper.pdf)



[CVPR19] Expressive Body Capture: 3D Hands, Face, and Body from a Single Image [[project page]](https://smpl-x.is.tue.mpg.de/) [[pdf]](https://ps.is.tuebingen.mpg.de/uploads_file/attachment/attachment/497/SMPL-X.pdf)



[CVPR18 Oral] Total Capture: A 3D Deformation Model for Tracking Faces, Hands, and Bodies [[project page]](http://www.cs.cmu.edu/~hanbyulj/totalcapture/) [[pdf]](http://openaccess.thecvf.com/content_cvpr_2018/papers/Joo_Total_Capture_A_CVPR_2018_paper.pdf)



[CVPR18] End-to-end recovery of human shape and pose [[project page]](https://akanazawa.github.io/hmr/) [[code and data]](https://github.com/akanazawa/hmr) [[pdf]](https://arxiv.org/pdf/1712.06584.pdf)



[CVPR17] Unite the people: Closing the loop between 3d and 2d human representations [[project page(code and data)]](http://files.is.tuebingen.mpg.de/classner/up/) [[pdf]](https://arxiv.org/pdf/1701.02468.pdf)



[BMVC17] Indirect deep structured learning for 3D human body shape and pose prediction [[pdf]](http://mi.eng.cam.ac.uk/~cipolla/publications/inproceedings/2017-BMVC-3D-body-indirect.pdf)

  

[ECCV16] Keep it SMPL: Automatic estimation of 3d human pose and shape from a single image [[code]](https://github.com/genki-ist/simplify) [[pdf]](https://arxiv.org/pdf/1607.08128.pdf)



[SIGGRAPH_Asia15] SMPL: A skinned multi-person linear model [[project page]](http://smpl.is.tue.mpg.de/)[[pdf]](http://files.is.tue.mpg.de/black/papers/SMPL2015.pdf)



[TOG14] Mosh: Motion and shape capture from sparse markers [[project page]](https://ps.is.tuebingen.mpg.de/research_projects/mosh) [[pdf]](http://files.is.tue.mpg.de/black/papers/MoSh.pdf)



[CVPR10] Multilinear pose and body shape estimation of dressed subjects from image sets [[pdf]](http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.167.8773&rep=rep1&type=pdf)



[ICCV09] Estimating Human Shape and Pose from a Single Image [[pdf]](http://files.is.tue.mpg.de/black/papers/guanICCV09.pdf)



[CVPR07] Detailed human shape and pose from images [[pdf]](http://www.cs.cmu.edu/~jkh/gnhm_08/balan07imscape.pdf)



[SIGGRAPH05] SCAPE: shape completion and animation of people [[project page]](http://robotics.stanford.edu/~drago/Projects/scape/scape.html) [[pdf]](http://robots.stanford.edu/papers/anguelov.shapecomp.pdf)



[CVIU01] Tracking and modeling people in video sequences [[pdf]](http://luthuli.cs.uiuc.edu/~daf/courses/appcv/papers/ankers01tracking.pdf)



## Single-view Reconstruction



[ICCV19] Tex2Shape: Detailed Full Human Body Geometry From a Single Image [[pdf]](http://openaccess.thecvf.com/content_ICCV_2019/papers/Alldieck_Tex2Shape_Detailed_Full_Human_Body_Geometry_From_a_Single_Image_ICCV_2019_paper.pdf)



[ICCV19] PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization [[pdf]](http://openaccess.thecvf.com/content_ICCV_2019/papers/Saito_PIFu_Pixel-Aligned_Implicit_Function_for_High-Resolution_Clothed_Human_Digitization_ICCV_2019_paper.pdf)



[ICCV19] Moulding Humans: Non-parametric 3D Human Shape Estimation from Single Images [[pdf]](https://arxiv.org/pdf/1908.00439.pdf)



[ICCV19] 3DPeople: Modeling the Geometry of Dressed Humans [[pdf]](https://arxiv.org/pdf/1904.04571.pdf)



[ICCV19] DeepHuman: 3D Human Reconstruction From a Single Image [[pdf]](http://www.liuyebin.com/deephuman/assets/DeepHuman.pdf)



[ICCV19] A Neural Network for Detailed Human Depth Estimation From a Single Image [[pdf]](http://openaccess.thecvf.com/content_ICCV_2019/papers/Tang_A_Neural_Network_for_Detailed_Human_Depth_Estimation_From_a_ICCV_2019_paper.pdf)



[ICCV19] Delving Deep Into Hybrid Annotations for 3D Human Recovery in the Wild [[pdf]](http://openaccess.thecvf.com/content_ICCV_2019/papers/Rong_Delving_Deep_Into_Hybrid_Annotations_for_3D_Human_Recovery_in_ICCV_2019_paper.pdf)



[CVPR19 Oral] SiCloPe: Silhouette-Based Clothed People [[pdf]](https://arxiv.org/pdf/1901.00049.pdf)



[CVPR19 Oral] Convolutional Mesh Regression for Single-Image Human Shape Reconstruction [[pdf]](http://www.cis.upenn.edu/~kostas/mypub.dir/kolotouros19cvpr.pdf)



[CVPR19 Oral] Detailed Human Shape Estimation from a Single Image by Hierarchical mesh deformation [[pdf]](https://arxiv.org/pdf/1904.10506.pdf)



[CVPR19] Learning to Reconstruct People in Clothing from a Single RGB Camera  [[project page]](https://virtualhumans.mpi-inf.mpg.de/octopus/) [[pdf]](https://arxiv.org/pdf/1903.05885.pdf)



[CVPR19] SimulCap: Single-View Human Performance Capture with Cloth Simulation [[pdf]](https://arxiv.org/abs/1903.06323)



[CVPR19] Photo Wake-Up: 3D Character Animation from a Single Photo [[project page]](https://grail.cs.washington.edu/projects/wakeup/) [[pdf]](https://arxiv.org/abs/1812.02246)



[TOG19] LiveCap: Real-time Human Performance Capture from Monocular Video [[project page]](https://gvv.mpi-inf.mpg.de/projects/LiveCap/) [[pdf]](https://gvv.mpi-inf.mpg.de/projects/LiveCap/data/livecap.pdf)



[CVPR18] End-to-end recovery of human shape and pose [[project page]](https://akanazawa.github.io/hmr/) [[code and data]](https://github.com/akanazawa/hmr) [[pdf]](https://arxiv.org/pdf/1712.06584.pdf)



[3DV18] Neural Body Fitting: Unifying Deep Learning and Model-Based Human Pose [[pdf]](https://arxiv.org/pdf/1808.05942.pdf)



[ICCV09] Estimating Human Shape and Pose from a Single Image [[pdf]](http://files.is.tue.mpg.de/black/papers/guanICCV09.pdf)



## 4D-Scans



[SIGGRAPH17] ClothCap: seamless 4D clothing capture and retargeting [[project page]](http://clothcap.is.tue.mpg.de/) [[pdf]](http://delivery.acm.org/10.1145/3080000/3073711/a73-pons-moll.pdf?ip=104.174.111.226&id=3073711&acc=OA&key=4D4702B0C3E38B35%2E4D4702B0C3E38B35%2E4D4702B0C3E38B35%2EA3ADFD50D6708552&__acm__=1557388386_0a9b1d6d188b8f850bf8b5f190d8060e)



## Datasets and Code




MPI datasets and code[[Link]](https://ps.is.tuebingen.mpg.de/research_fields/datasets-and-code)



BUFF[[Link]](http://buff.is.tue.mpg.de/)



Dynamic FAUST[[Link]](https://ps.is.tuebingen.mpg.de/publications/dfaust-cvpr-2017)



CVSSP3D[[Link]](https://www.cvssp.org/data/cvssp3d/)



Mixamo[[Link]](https://www.mixamo.com/)



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



3DPeople[[Link]](https://www.albertpumarola.com/research/3DPeople/index.html)



THuman[[Link]](https://github.com/ZhengZerong/DeepHuman/tree/master/THUmanDataset)



RenderPeople[[Link]](https://renderpeople.com/)



CLOTH3D[[Link]](https://arxiv.org/pdf/1912.02792.pdf)(not released yet)



Multi-Garment Net[[Link]](https://github.com/bharat-b7/MultiGarmentNetwork)