Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.
Awesome Lists | Featured Topics | Projects
https://github.com/bluestyle97/awesome-3d-reconstruction-papers

A collection of 3D reconstruction papers in the deep learning era.
https://github.com/bluestyle97/awesome-3d-reconstruction-papers
List: awesome-3d-reconstruction-papers
Last synced: about 2 months ago
JSON representation
A collection of 3D reconstruction papers in the deep learning era.
Host: GitHub
URL: https://github.com/bluestyle97/awesome-3d-reconstruction-papers
Owner: bluestyle97
Created: 2021-04-08T12:22:49.000Z (over 3 years ago)
Default Branch: main
Last Pushed: 2023-12-11T14:52:28.000Z (about 1 year ago)
Last Synced: 2024-05-23T03:00:49.841Z (7 months ago)
Size: 311 KB
Stars: 680
Watchers: 21
Forks: 50
Open Issues: 0
Metadata Files:
- Readme: README.md
Awesome Lists containing this project

ultimate-awesome - awesome-3d-reconstruction-papers - A collection of 3D reconstruction papers in the deep learning era. (Other Lists / Monkey C Lists)
README

        # Awesome 3D Reconstruction Papers

[![Awesome](https://awesome.re/badge.svg)](https://awesome.re)

A collection of 3D reconstruction papers in the deep learning era. Feel free to contribute :)

Table of Contents

=================

  * [Object-level](#object-level)

     * [Single-view](#single-view)

     * [Multi-view](#multi-view)

     * [Unsupervised](#unsupervised)

  * [Scene-level](#scene-level)

     * [Single-view](#single-view-1)

     * [Multi-view](#multi-view-1)

  * [Neural-Surface](#neural-surface)

     * [Multi-view](#multi-view-2)

     * [Point-cloud](#point-cloud)

     * [RGB-D](#rgb-d)

  * [Survey](#survey)

## Object-level

### Single-view

| Paper | Representation| Publisher | Project/Code |

| :----------------------------------------------------------: | :-------: | :-------: | :-----------------------------------------------------: |

| [A Point Set Generation Network for 3D Object Reconstruction from a Single Image](https://openaccess.thecvf.com/content_cvpr_2017/html/Fan_A_Point_Set_CVPR_2017_paper.html) | Point Cloud | CVPR 2017 | [Code](https://github.com/fanhqme/PointSetGeneration) |

| [SurfNet: Generating 3D Shape Surfaces Using Deep Residual Networks](https://openaccess.thecvf.com/content_cvpr_2017/html/Sinha_SurfNet_Generating_3D_CVPR_2017_paper.html) | Mesh | CVPR 2017 | [Code](https://github.com/sinhayan/surfnet) |

| [OctNet: Learning Deep 3D Representations at High Resolutions](https://openaccess.thecvf.com/content_cvpr_2017/html/Riegler_OctNet_Learning_Deep_CVPR_2017_paper.html) | Voxel | CVPR 2017 | [Code](https://github.com/griegler/octnet) |

| [Rethinking Reprojection: Closing the Loop for Pose-Aware Shape Reconstruction From a Single Image](https://openaccess.thecvf.com/content_iccv_2017/html/Zhu_Rethinking_Reprojection_Closing_ICCV_2017_paper.html) | Voxel | ICCV 2017 | / |

| [MarrNet: 3D Shape Reconstruction via 2.5D Sketches](https://proceedings.neurips.cc/paper/2017/hash/ad972f10e0800b49d76fed33a21f6698-Abstract.html) | Voxel | NIPS 2017 | [Project](http://marrnet.csail.mit.edu/) |

| [Hierarchical Surface Prediction for 3D Object Reconstruction](https://arxiv.org/abs/1704.00710) | Voxel | 3DV 2017 | [Code](https://github.com/chaene/hsp) |

| [Image2Mesh: A Learning Framework for Single Image 3D Reconstruction](https://arxiv.org/abs/1711.10669) | Mesh | ACCV 2018 | [Code](https://github.com/jhonykaesemodel/image2mesh) |

| [Learning Efficient Point Cloud Generation for Dense 3D Object Reconstruction](https://aaai.org/ocs/index.php/AAAI/AAAI18/paper/view/16530) | Point Cloud | AAAI 2018 | [Project](https://chenhsuanlin.bitbucket.io/3D-point-cloud-generation/) |

| [A Papier-Mâché Approach to Learning 3D Surface Generation](https://openaccess.thecvf.com/content_cvpr_2018/html/Groueix_A_Papier-Mache_Approach_CVPR_2018_paper.html) | Mesh | CVPR 2018 | [Project](http://imagine.enpc.fr/~groueixt/atlasnet/) |

| [Pixels, voxels, and views: A study of shape representations for single view 3D object shape prediction](https://openaccess.thecvf.com/content_cvpr_2018/html/Shin_Pixels_Voxels_and_CVPR_2018_paper.html) | Generic | CVPR 2018 | [Project](https://www.ics.uci.edu/~daeyuns/pixels-voxels-views/) |

| [Im2Struct: Recovering 3D Shape Structure From a Single RGB Image](https://openaccess.thecvf.com/content_cvpr_2018/html/Niu_Im2Struct_Recovering_3D_CVPR_2018_paper.html) | Parts | CVPR 2018 | [Code](https://github.com/chengjieniu/Im2Struct) |

| [Matryoshka Networks: Predicting 3D Geometry via Nested Shape Layers](https://openaccess.thecvf.com/content_cvpr_2018/html/Richter_Matryoshka_Networks_Predicting_CVPR_2018_paper.html) | Voxel | CVPR 2018 | [Code](https://bitbucket.org/visinf/projects-2018-matryoshka/src/master/) |

| [Multi-View Consistency as Supervisory Signal for Learning Shape and Pose Prediction](https://openaccess.thecvf.com/content_cvpr_2018/html/Tulsiani_Multi-View_Consistency_as_CVPR_2018_paper.html) | Voxel | CVPR 2018 | [Project](https://shubhtuls.github.io/mvcSnP/) |

| [Efficient Dense Point Cloud Object Reconstruction using Deformation Vector Fields](https://openaccess.thecvf.com/content_ECCV_2018/html/Kejie_Li_Efficient_Dense_Point_ECCV_2018_paper.html) | Point Cloud | ECCV 2018 | / |

| [GAL: Geometric Adversarial Loss for Single-View 3D-Object Reconstruction](https://openaccess.thecvf.com/content_ECCV_2018/html/Li_Jiang_GAL_Geometric_Adversarial_ECCV_2018_paper.html) | Point Cloud | ECCV 2018 | / |

| [Learning Category-Specific Mesh Reconstruction from Image Collections](https://openaccess.thecvf.com/content_ECCV_2018/html/Angjoo_Kanazawa_Learning_Category-Specific_Mesh_ECCV_2018_paper.html) | Mesh | ECCV 2018 | [Project](https://akanazawa.github.io/cmr/) |

| [Learning Shape Priors for Single-View 3D Completion and Reconstruction](https://openaccess.thecvf.com/content_ECCV_2018/html/Jiajun_Wu_Learning_3D_Shape_ECCV_2018_paper.html) | Voxel | ECCV 2018 | / |

| [Learning Single-View 3D Reconstruction with Limited Pose Supervision](https://openaccess.thecvf.com/content_ECCV_2018/html/Guandao_Yang_A_Unified_Framework_ECCV_2018_paper.html) | Voxel | ECCV 2018 | [Code](https://github.com/stevenygd/3d-recon) |

| [Pixel2Mesh: Generating 3D Mesh Models from Single RGB Images](https://openaccess.thecvf.com/content_ECCV_2018/html/Nanyang_Wang_Pixel2Mesh_Generating_3D_ECCV_2018_paper.html) | Mesh | ECCV 2018 | [Code](https://github.com/nywang16/Pixel2Mesh) |

| [Residual MeshNet: Learning to Deform Meshes for Single-View 3D Reconstruction](https://ieeexplore.ieee.org/abstract/document/8491025) | Mesh | 3DV 2018 | / |

| [Learning to Reconstruct Shapes from Unseen Classes](https://proceedings.neurips.cc/paper/2018/hash/208e43f0e45c4c78cafadb83d2888cb6-Abstract.html) | Generic | NIPS 2018 | [Project](http://genre.csail.mit.edu/) |

| [Multi-View Silhouette and Depth Decomposition for High Resolution 3D Object Representation](https://proceedings.neurips.cc/paper/2018/hash/39ae2ed11b14a4ccb41d35e9d1ba5d11-Abstract.html) | Voxel | NIPS 2018 | [Code](https://github.com/EdwardSmith1884/Multi-View-Silhouette-and-Depth-Decomposition-for-High-Resolution-3D-Object-Representation) |

| [MVPNet: Multi-View Point Regression Networks for 3D Object Reconstruction from A Single Image](https://ojs.aaai.org/index.php/AAAI/article/view/4923) | Point Cloud | AAAI 2019 | [Project](https://jingluw.github.io/projects/mvpnet/) |

| [Deep Single-View 3D Object Reconstruction with Visual Hull Embedding](https://ojs.aaai.org//index.php/AAAI/article/view/4922) | Voxel | AAAI 2019 | [Code](https://github.com/HanqingWangAI/PSVH-3d-reconstruction) |

| [Occupancy Networks: Learning 3D Reconstruction in Function Space](https://openaccess.thecvf.com/content_CVPR_2019/html/Mescheder_Occupancy_Networks_Learning_3D_Reconstruction_in_Function_Space_CVPR_2019_paper.html) | Implicit | CVPR 2019 | [Code](https://github.com/autonomousvision/occupancy_networks) |

| [Learning Implicit Fields for Generative Shape Modeling](https://openaccess.thecvf.com/content_CVPR_2019/html/Chen_Learning_Implicit_Fields_for_Generative_Shape_Modeling_CVPR_2019_paper.html) | Implicit | CVPR 2019 | [Project](https://www.sfu.ca/~zhiqinc/imgan/Readme.html) |

| [A Skeleton-Bridged Deep Learning Approach for Generating Meshes of Complex Topologies From Single RGB Images](https://openaccess.thecvf.com/content_CVPR_2019/html/Tang_A_Skeleton-Bridged_Deep_Learning_Approach_for_Generating_Meshes_of_Complex_CVPR_2019_paper.html) | Mesh | CVPR 2019 | [Code](https://github.com/tangjiapeng/SkeletonBridgeRecon) |

| [What Do Single-view 3D Reconstruction Networks Learn?](https://openaccess.thecvf.com/content_CVPR_2019/html/Tatarchenko_What_Do_Single-View_3D_Reconstruction_Networks_Learn_CVPR_2019_paper.html) | Generic | CVPR 2019 | [Code](https://github.com/lmb-freiburg/what3d) |

| [Deep Level Sets: Implicit Surface Representations for 3D Shape Inference](https://arxiv.org/abs/1901.06802) | Implicit | arXiv 2019 | / |

| [Deep Mesh Reconstruction From Single RGB Images via Topology Modification Networks](https://openaccess.thecvf.com/content_ICCV_2019/html/Pan_Deep_Mesh_Reconstruction_From_Single_RGB_Images_via_Topology_Modification_ICCV_2019_paper.html) | Mesh | ICCV 2019 | [Code](https://github.com/jnypan/TMNet) |

| [Deep Meta Functionals for Shape Representation](https://openaccess.thecvf.com/content_ICCV_2019/html/Littwin_Deep_Meta_Functionals_for_Shape_Representation_ICCV_2019_paper.html) | Implicit | ICCV 2019 | [Code](https://github.com/gidilittwin/Deep-Meta) |

| [GraphX-Convolution for Point Cloud Deformation in 2D-to-3D Conversion](https://openaccess.thecvf.com/content_ICCV_2019/html/Nguyen_GraphX-Convolution_for_Point_Cloud_Deformation_in_2D-to-3D_Conversion_ICCV_2019_paper.html) | Point Cloud | ICCV 2019 | [Code](https://github.com/ywcmaike/pcdnet) |

| [Pix2Vox: Context-Aware 3D Reconstruction From Single and Multi-View Images](https://openaccess.thecvf.com/content_ICCV_2019/html/Xie_Pix2Vox_Context-Aware_3D_Reconstruction_From_Single_and_Multi-View_Images_ICCV_2019_paper.html) | Voxel | ICCV 2019 | [Code](https://github.com/hzxie/Pix2Vox) |

| [Domain-Adaptive Single-View 3D Reconstruction](https://openaccess.thecvf.com/content_ICCV_2019/html/Pinheiro_Domain-Adaptive_Single-View_3D_Reconstruction_ICCV_2019_paper.html) | Voxel | ICCV 2019 | [Code](https://github.com/Gitikameher/Domain-Adaptive-Single-View-3D-Reconstruction) |

| [Few-Shot Generalization for Single-Image 3D Reconstruction via Priors](https://openaccess.thecvf.com/content_ICCV_2019/html/Wallace_Few-Shot_Generalization_for_Single-Image_3D_Reconstruction_via_Priors_ICCV_2019_paper.html) | Voxel | ICCV 2019 | [Code](https://github.com/BramSW/iccv_2019_few_shot_3d_wallace) |

| [DISN: Deep Implicit Surface Network for High-quality Single-view 3D Reconstruction](https://proceedings.neurips.cc/paper/2019/hash/39059724f73a9969845dfe4146c5660e-Abstract.html) | Implicit | NIPS 2019 | [Code](https://github.com/laughtervv/DISN) |

| [Front2Back: Single View 3D Shape Reconstruction via Front to Back Prediction](https://openaccess.thecvf.com/content_CVPR_2020/html/Yao_Front2Back_Single_View_3D_Shape_Reconstruction_via_Front_to_Back_CVPR_2020_paper.html) | Mesh | CVPR 2020 | [Code](https://github.com/rozentill/Front2Back) |

| [BSP-Net: Generating Compact Meshes via Binary Space Partitioning](https://openaccess.thecvf.com/content_CVPR_2020/html/Chen_BSP-Net_Generating_Compact_Meshes_via_Binary_Space_Partitioning_CVPR_2020_paper.html) | Mesh | CVPR 2020 | [Project](https://bsp-net.github.io/) |

| [Height and Uprightness Invariance for 3D Prediction From a Single View](https://openaccess.thecvf.com/content_CVPR_2020/html/Baradad_Height_and_Uprightness_Invariance_for_3D_Prediction_From_a_Single_CVPR_2020_paper.html) | Point Cloud | CVPR 2020 | [Code](https://github.com/mbaradad/im2pcl) |

| [Implicit Functions in Feature Space for 3D Shape Reconstruction and Completion](https://openaccess.thecvf.com/content_CVPR_2020/html/Chibane_Implicit_Functions_in_Feature_Space_for_3D_Shape_Reconstruction_and_CVPR_2020_paper.html) | Implicit | CVPR 2020 | [Project](https://virtualhumans.mpi-inf.mpg.de/ifnets/) |

| [Unsupervised Learning of Probably Symmetric Deformable 3D Objects From Images in the Wild](https://openaccess.thecvf.com/content_CVPR_2020/html/Wu_Unsupervised_Learning_of_Probably_Symmetric_Deformable_3D_Objects_From_Images_CVPR_2020_paper.html) | Mesh | CVPR 2020 | [Project](https://www.robots.ox.ac.uk/~vgg/blog/unsupervised-learning-of-probably-symmetric-deformable-3d-objects-from-images-in-the-wild.html?image=004_face&type=human) |

| [CvxNet: Learnable Convex Decomposition](https://openaccess.thecvf.com/content_CVPR_2020/html/Deng_CvxNet_Learnable_Convex_Decomposition_CVPR_2020_paper.html) | Primitive | CVPR 2020 | [Project](https://cvxnet.github.io/) |

| [Deep Local Shapes: Learning Local SDF Priors for Detailed 3D Reconstruction](https://www.ecva.net/papers/eccv_2020/papers_ECCV/html/6873_ECCV_2020_paper.php) | Implicit | ECCV 2020 | [Code](https://github.com/Kamysek/DeepLocalShapes) |

| [Few-Shot Single-View 3-D Object Reconstruction with Compositional Priors](https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123700613.pdf) | Voxel | ECCV 2020 | [Code](https://github.com/JeremyFisher/few_shot_3dr) |

| [GSIR: Generalizable 3D Shape Interpretation and Reconstruction](https://www.ecva.net/papers/eccv_2020/papers_ECCV/html/1955_ECCV_2020_paper.php) | Voxel | ECCV 2020 | / |

| [DR-KFS: A Differentiable Visual Similarity Metric for 3D Shape Reconstruction](https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123660290.pdf) | Mesh | ECCV 2020 | / |

| [Self-supervised Single-view 3D Reconstruction via Semantic Consistency](https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123590664.pdf) | Mesh | ECCV 2020 | [Project](https://sites.google.com/nvidia.com/unsup-mesh-2020) |

| [Shape and Viewpoint without Keypoints](https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123600086.pdf) | Mesh | ECCV 2020 | [Project](https://shubham-goel.github.io/ucmr/) |

| [Ladybird: Quasi-Monte Carlo Sampling for Deep Implicit Field Based 3D Reconstruction with Symmetry](https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123460239.pdf) | Mesh | ECCV 2020 | [Code](https://github.com/FuxiCV/Ladybird) |

| [Learning Deformable Tetrahedral Meshes for 3D Reconstruction](https://proceedings.neurips.cc//paper/2020/file/7137debd45ae4d0ab9aa953017286b20-Paper.pdf) | Mesh | NIPS 2020 | [Project](https://nv-tlabs.github.io/DefTet/) |

| [SDF-SRN: Learning Signed Distance 3D Object Reconstruction from Static Images](https://papers.nips.cc/paper/2020/file/83fa5a432ae55c253d0e60dbfa716723-Paper.pdf) | Implicit | NIPS 2020 | [Project](https://chenhsuanlin.bitbucket.io/signed-distance-SRN/) |

| [UCLID-Net: Single View Reconstruction in Object Space](https://papers.nips.cc/paper/2020/hash/21327ba33b3689e713cdff1641128004-Abstract.html) | Mesh | NIPS 2020 | [Code](https://github.com/cvlab-epfl/UCLID-Net) |

| [Pix2Vox++: Multi-scale Context-aware 3D Object Reconstruction from Single and Multiple Images](https://arxiv.org/abs/2006.12250) | Voxel | IJCV 2020 | [Code](https://gitlab.com/hzxie/Pix2Vox) |

| [D2IM-Net: Learning Detail Disentangled Implicit Fields From Single Images](https://openaccess.thecvf.com/content/CVPR2021/html/Li_D2IM-Net_Learning_Detail_Disentangled_Implicit_Fields_From_Single_Images_CVPR_2021_paper.html) | Implicit | CVPR 2021 | [Code](https://github.com/ManyiLi12345/D2IM-Net) |

| [NeRD: Neural 3D Reflection Symmetry Detector](https://openaccess.thecvf.com/content/CVPR2021/html/Zhou_NeRD_Neural_3D_Reflection_Symmetry_Detector_CVPR_2021_paper.html) | / | CVPR 2021 | [Code](https://github.com/zhou13/nerd) |

| [Fostering Generalization in Single-view 3D Reconstruction by Learning a Hierarchy of Local and Global Shape Priors](https://openaccess.thecvf.com/content/CVPR2021/html/Bechtold_Fostering_Generalization_in_Single-View_3D_Reconstruction_by_Learning_a_Hierarchy_CVPR_2021_paper.html) | Implicit | CVPR 2021 | [Code](https://github.com/boschresearch/HierarchicalPriorNetworks) |

| [Single-View 3D Object Reconstruction From Shape Priors in Memory](https://openaccess.thecvf.com/content/CVPR2021/html/Yang_Single-View_3D_Object_Reconstruction_From_Shape_Priors_in_Memory_CVPR_2021_paper.html) | Voxel | CVPR 2021 | [Project](https://cvxnet.github.io/) |

| [Implicit Surface Representations as Layers in Neural Networks](https://openaccess.thecvf.com/content_ICCV_2019/html/Michalkiewicz_Implicit_Surface_Representations_As_Layers_in_Neural_Networks_ICCV_2019_paper.html) | Implicit | ICCV 2021 | / |

| [Ray-ONet: Efficient 3D Reconstruction From A Single RGB Image](https://arxiv.org/abs/2107.01899) | Implicit | BMVC 2021 | [Project](https://rayonet.active.vision/) |

| [Learning Anchored Unsigned Distance Functions with Gradient Direction Alignment for Single-view Garment Reconstruction](https://openaccess.thecvf.com/content/ICCV2021/html/Zhao_Learning_Anchored_Unsigned_Distance_Functions_With_Gradient_Direction_Alignment_for_ICCV_2021_paper.html) | Implicit | ICCV 2021 | [Code](https://github.com/zhaofang0627/AnchorUDF) |

| [Geometric Granularity Aware Pixel-to-Mesh](https://openaccess.thecvf.com/content/ICCV2021/html/Shi_Geometric_Granularity_Aware_Pixel-To-Mesh_ICCV_2021_paper.html) | Mesh | ICCV 2021 | / |

| [Sketch2Mesh: Reconstructing and Editing 3D Shapes from Sketches](https://openaccess.thecvf.com/content/ICCV2021/html/Guillard_Sketch2Mesh_Reconstructing_and_Editing_3D_Shapes_From_Sketches_ICCV_2021_paper.html) | Mesh | ICCV 2021 | [Code](https://github.com/cvlab-epfl/sketch2mesh) |

| [3DIAS: 3D Shape Reconstruction With Implicit Algebraic Surfaces](https://openaccess.thecvf.com/content/ICCV2021/html/Yavartanoo_3DIAS_3D_Shape_Reconstruction_With_Implicit_Algebraic_Surfaces_ICCV_2021_paper.html) | Primitive | ICCV 2021 | [Project](https://myavartanoo.github.io/3dias/) |

| [A Dataset-Dispersion Perspective on Reconstruction Versus Recognition in Single-View 3D Reconstruction Networks](https://arxiv.org/abs/2111.15158) | Point Cloud | 3DV 2021 | [Code](https://github.com/yefanzhou/dispersion-score) |

| [3D Reconstruction of Novel Object Shapes from Single Images](https://arxiv.org/abs/2006.07752) | Implicit | 3DV 2021 | [Project](https://devlearning-gt.github.io/3DShapeGen/) |

| [AutoSDF: Shape Priors for 3D Completion, Reconstruction and Generation](https://arxiv.org/abs/2203.09516) | Implicit | CVPR 2022 | [Project](https://yccyenchicheng.github.io/AutoSDF/) |

| [3D Shape Reconstruction from 2D Images with Disentangled Attribute Flow](https://arxiv.org/abs/2203.15190) | Point Cloud | CVPR 2022 | [Code](https://github.com/junshengzhou/3dattriflow) |

| [Pre-train, Self-train, Distill: A simple recipe for Supersizing 3D Reconstruction](https://arxiv.org/abs/2203.15190) | Implicit | CVPR 2022 | [Project](https://shubhtuls.github.io/ss3d/) |

| [Neural Template: Topology-aware Reconstruction and Disentangled Generation of 3D Meshes](https://openaccess.thecvf.com/content/CVPR2022/html/Hui_Neural_Template_Topology-Aware_Reconstruction_and_Disentangled_Generation_of_3D_Meshes_CVPR_2022_paper.html) | Hybrid | CVPR 2022 | [Code](https://github.com/edward1997104/Neural-Template) |

| [SkeletonNet: A Topology-Preserving Solution for Learning Mesh Reconstruction of Object Surfaces from RGB Images](https://arxiv.org/abs/2008.05742) | Mesh | TPAMI 2022 | [Code](https://github.com/tangjiapeng/SkeletonNet) |

| [Training Data Generating Networks: Shape Reconstruction via Bi-level Optimization](https://arxiv.org/abs/2010.08276) | Implicit | ICLR 2022 | / |

| [Structural Causal 3D Reconstruction](https://arxiv.org/abs/2207.10156) | Hybrid | ECCV 2022 | / |

| [Few-shot Single-view 3D Reconstruction with Memory Prior Contrastive Network](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136610054.pdf) | Voxel | ECCV 2022 | / |

| [Semi-Supervised Single-View 3D Reconstruction via Prototype Shape Priors](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136610528.pdf) | Voxel | ECCV 2022 | / |

| [Single-view 3D Scene Reconstruction with High-fidelity Shape and Texture](https://arxiv.org/pdf/2311.00457.pdf) | Implicit | 3DV 2024 | [Code](https://github.com/DaLi-Jack/SSR-code) |

### Multi-view

|                            Paper                             | Representation | Publisher |                         Project/Code                         |

| :----------------------------------------------------------: | :------------: | :-------: | :----------------------------------------------------------: |

| [3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction](https://arxiv.org/abs/1604.00449) |     Voxel      | ECCV 2016 |        [Code](https://github.com/chrischoy/3D-R2N2)        |

| [3D Shape Induction from 2D Views of Multiple Objects](https://arxiv.org/abs/1612.05872) |     Voxel      | 3DV 2017  |      [Code](https://github.com/matheusgadelha/PrGAN)       |

| [Learning Efficient Point Cloud Generation for Dense 3D Object Reconstruction](https://www.aaai.org/ocs/index.php/AAAI/AAAI18/paper/download/16530/16302) |  Point Cloud   | AAAI 2018 | [Project](https://chenhsuanlin.bitbucket.io/3D-point-cloud-generation/) |

| [Conditional Single-view Shape Generation for Multi-view Stereo Reconstruction](https://openaccess.thecvf.com/content_CVPR_2019/html/Wei_Conditional_Single-View_Shape_Generation_for_Multi-View_Stereo_Reconstruction_CVPR_2019_paper.html) |  Point Cloud   | CVPR 2019 |      [Code](https://github.com/weiyithu/OptimizeMVS)       |

| [Pixel2Mesh++: Multi-View 3D Mesh Generation via Deformation](https://openaccess.thecvf.com/content_ICCV_2019/html/Wen_Pixel2Mesh_Multi-View_3D_Mesh_Generation_via_Deformation_ICCV_2019_paper.html) |      Mesh      | ICCV 2019 |  [Project](https://walsvid.github.io/Pixel2MeshPlusPlus/)  |

| [Multiview Aggregation for Learning Category-Specific Shape Reconstruction](https://papers.nips.cc/paper/8506-multiview-aggregation-for-learning-category-specific-shape-reconstruction.pdf) |  Point Cloud   | NIPS 2019 |     [Code](https://github.com/drsrinathsridhar/xnocs)      |

| [Pix2Surf: Learning Parametric 3D Surface Models of Objects from Images](https://arxiv.org/abs/2008.07760) |      Patches      | ECCV 2020  |        [Project](https://geometry.stanford.edu/projects/pix2surf/)         |

| [Multi-view 3D Reconstruction with Transformers](https://openaccess.thecvf.com/content/ICCV2021/html/Wang_Multi-View_3D_Reconstruction_With_Transformers_ICCV_2021_paper.html) |      Voxel      | ICCV 2021  | / |

| [3D-C2FT: Coarse-to-fine Transformer for Multi-view 3D Reconstruction](https://arxiv.org/abs/2205.14575) |      Voxel      | ACCV 2022  | / |

| [FvOR: Robust Joint Shape and Pose Optimization for Few-view Object Reconstruction](https://openaccess.thecvf.com/content/CVPR2022/html/Yang_FvOR_Robust_Joint_Shape_and_Pose_Optimization_for_Few-View_Object_CVPR_2022_paper.html) |      Implicit      | CVPR 2022  | [Code](https://github.com/zhenpeiyang/FvOR/) |

| [FOUND: Foot Optimisation with Uncertain Normals for Surface Deformation using Synthetic Data](https://ollieboyne.com/FOUND) | Mesh | WACV 2024 | [Code](https://github.com/OllieBoyne/FOUND) |

### Unsupervised

|                            Paper                             | Representation | Publisher |                         Project/Code                         |

| :----------------------------------------------------------: | :------------: | :-------: | :----------------------------------------------------------: |

| [Perspective Transformer Nets: Learning Single-View 3D Object Reconstruction without 3D Supervision](https://proceedings.neurips.cc/paper/2016/hash/e820a45f1dfc7b95282d10b6087e11c0-Abstract.html) | Voxel | NIPS 2016 |      [Code](https://github.com/xcyan/nips16_PTN)      |

| [Multi-view Supervision for Single-View Reconstruction via Differentiable Ray Consistency](https://openaccess.thecvf.com/content_cvpr_2017/html/Tulsiani_Multi-View_Supervision_for_CVPR_2017_paper.html) |      Voxel      | CVPR 2017 |        [Project](https://shubhtuls.github.io/drc/)         |

| [Rethinking Reprojection: Closing the Loop for Pose-Aware Shape Reconstruction from a Single Image](https://openaccess.thecvf.com/content_iccv_2017/html/Zhu_Rethinking_Reprojection_Closing_ICCV_2017_paper.html) |      Voxel      | ICCV 2017 |  /  |

| [Learning Category-Specific Mesh Reconstruction from Image Collections](https://openaccess.thecvf.com/content_ECCV_2018/html/Angjoo_Kanazawa_Learning_Category-Specific_Mesh_ECCV_2018_paper.html) |      Mesh      | ECCV 2018 |        [Project](https://akanazawa.github.io/cmr/)         |

| [Learning Single-View 3D Reconstruction with Limited Pose Supervision](https://openaccess.thecvf.com/content_ECCV_2018/html/Guandao_Yang_A_Unified_Framework_ECCV_2018_paper.html) |      Voxel      | ECCV 2018 |        [Code](https://github.com/stevenygd/3d-recon)         |

| [Multi-View Consistency as Supervisory Signal for Learning Shape and Pose Prediction](https://openaccess.thecvf.com/content_cvpr_2018/html/Tulsiani_Multi-View_Consistency_as_CVPR_2018_paper.html) |      Voxel      | CVPR 2018 |        [Project](https://shubhtuls.github.io/mvcSnP/)         |

| [Learning View Priors for Single-view 3D Reconstruction](https://openaccess.thecvf.com/content_CVPR_2019/html/Kato_Learning_View_Priors_for_Single-View_3D_Reconstruction_CVPR_2019_paper.html) |      Mesh      | CVPR 2019 |        [Code](https://github.com/hiroharu-kato/view_prior_learning)         |

| [Escaping Plato's Cave: 3D Shape From Adversarial Rendering](https://openaccess.thecvf.com/content_ICCV_2019/html/Henzler_Escaping_Platos_Cave_3D_Shape_From_Adversarial_Rendering_ICCV_2019_paper.html) |      Voxel      | ICCV 2019 |        [Project](https://geometry.cs.ucl.ac.uk/projects/2019/platonicgan/)         |

| [Learning to Infer Implicit Surfaces without 3D Supervision](https://proceedings.neurips.cc/paper/2019/hash/bdf3fd65c81469f9b74cedd497f2f9ce-Abstract.html) |      Implicit      | NIPS 2019 |  /  |

| [Learning to Predict 3D Objects with an Interpolation-based Differentiable Renderer](https://proceedings.neurips.cc/paper/2019/hash/f5ac21cd0ef1b88e9848571aeb53551a-Abstract.html) |      Mesh      | NIPS 2019 |        [Project](https://nv-tlabs.github.io/DIB-R/)         |

| [Unsupervised Learning of Probably Symmetric Deformable 3D Objects from Images in the Wild](https://openaccess.thecvf.com/content_CVPR_2020/html/Wu_Unsupervised_Learning_of_Probably_Symmetric_Deformable_3D_Objects_From_Images_CVPR_2020_paper.html) |      Mesh      | CVPR 2020 |        [Project](https://elliottwu.com/projects/20_unsup3d/)         |

| [Leveraging 2D Data to Learn Textured 3D Mesh Generation](https://openaccess.thecvf.com/content_CVPR_2020/html/Henderson_Leveraging_2D_Data_to_Learn_Textured_3D_Mesh_Generation_CVPR_2020_paper.html) |      Mesh      | CVPR 2020 |        [Code](https://github.com/pmh47/textured-mesh-gen)         |

| [Implicit Mesh Reconstruction from Unannotated Image Collections](https://arxiv.org/abs/2007.08504) |      Mesh      | arXiv 2020 |        [Project](https://shubhtuls.github.io/imr/)         |

| [Shape and Viewpoint without Keypoints](https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123600086.pdf) |      Mesh      | ECCV 2020 |        [Project](https://shubham-goel.github.io/ucmr/)         |

| [Self-supervised Single-view 3D Reconstruction via Semantic Consistency](https://arxiv.org/abs/2003.06473) |      Mesh      | ECCV 2020 |        [Project](https://sites.google.com/nvidia.com/unsup-mesh-2020)         |

| [SDF-SRN: Learning Signed Distance 3D Object Reconstruction from Static Images](https://proceedings.neurips.cc/paper/2020/hash/83fa5a432ae55c253d0e60dbfa716723-Abstract.html) |      Implicit      | NIPS 2020 |        [Project](https://chenhsuanlin.bitbucket.io/signed-distance-SRN/)         |

| [Shelf-Supervised Mesh Prediction in the Wild](https://openaccess.thecvf.com/content/CVPR2021/html/Ye_Shelf-Supervised_Mesh_Prediction_in_the_Wild_CVPR_2021_paper.html) |      Mesh      | CVPR 2021 |        [Project](https://judyye.github.io/ShSMesh/)         |

| [Fully Understanding Generic Objects: Modeling, Segmentation, and Reconstruction](https://openaccess.thecvf.com/content/CVPR2021/html/Liu_Fully_Understanding_Generic_Objects_Modeling_Segmentation_and_Reconstruction_CVPR_2021_paper.html) |      Implicit      | CVPR 2021 |        [Project](http://cvlab.cse.msu.edu/project-fully3dobject.html)         |

| [Self-Supervised 3D Mesh Reconstruction from Single Images](https://openaccess.thecvf.com/content/CVPR2021/html/Hu_Self-Supervised_3D_Mesh_Reconstruction_From_Single_Images_CVPR_2021_paper.html) |      Mesh      | CVPR 2021 |        [Code](https://github.com/dvlab-research/SMR)         |

| [View Generalization for Single Image Textured 3D Models](https://openaccess.thecvf.com/content/CVPR2021/html/Bhattad_View_Generalization_for_Single_Image_Textured_3D_Models_CVPR_2021_paper.html) |      Mesh      | CVPR 2021 |        [Project](https://nv-adlr.github.io/view-generalization)         |

| [Do 2D GANs Know 3D Shape? Unsupervised 3D shape reconstruction from 2D Image GANs](https://arxiv.org/abs/2011.00844) |      Mesh      | ICLR 2021 |        [Project](https://xingangpan.github.io/projects/GAN2Shape.html)         |

| [Image GANs meet Differentiable Rendering for Inverse Graphics and Interpretable 3D Neural Rendering](https://arxiv.org/abs/2010.09125) |      Mesh      | ICLR 2021 |        [Project](https://nv-tlabs.github.io/GANverse3D/)    |

| [Discovering 3D Parts from Image Collections](https://openaccess.thecvf.com/content/ICCV2021/html/Yao_Discovering_3D_Parts_From_Image_Collections_ICCV_2021_paper.html) |      Mesh      | ICCV 2021 |        [Project](https://chhankyao.github.io/lpd/)         |

| [Learning Canonical 3D Object Representation for Fine-Grained Recognition](https://openaccess.thecvf.com/content/ICCV2021/html/Joung_Learning_Canonical_3D_Object_Representation_for_Fine-Grained_Recognition_ICCV_2021_paper.html) |      Mesh      | ICCV 2021 |  /  |

| [Toward Realistic Single-View 3D Object Reconstruction with Unsupervised Learning from Multiple Images](https://openaccess.thecvf.com/content/ICCV2021/html/Ho_Toward_Realistic_Single-View_3D_Object_Reconstruction_With_Unsupervised_Learning_From_ICCV_2021_paper.html) |      Mesh      | ICCV 2021 |        [Code](https://github.com/VinAIResearch/LeMul)         |

| [Learning Generative Models of Textured 3D Meshes from Real-World Images](https://openaccess.thecvf.com/content/ICCV2021/html/Pavllo_Learning_Generative_Models_of_Textured_3D_Meshes_From_Real-World_Images_ICCV_2021_paper.html) |      Mesh      | ICCV 2021 |        [Code](https://github.com/dariopavllo/textured-3d-gan)         |

| [To The Point: Correspondence-driven monocular 3D category reconstruction](https://proceedings.neurips.cc/paper/2021/hash/40008b9a5380fcacce3976bf7c08af5b-Abstract.html) |      Mesh      | NIPS 2021 |        [Project](https://fkokkinos.github.io/to_the_point/)         |

| [Topologically-Aware Deformation Fields for Single-View 3D Reconstruction](https://openaccess.thecvf.com/content/CVPR2022/html/Duggal_Topologically-Aware_Deformation_Fields_for_Single-View_3D_Reconstruction_CVPR_2022_paper.html) |      Implicit      | CVPR 2022 |        [Project](https://shivamduggal4.github.io/tars-3D/)     |

| [2D GANs Meet Unsupervised Single-View 3D Reconstruction](https://arxiv.org/abs/2207.10183) |      Implicit      | ECCV 2022 |        [Project](http://cvlab.cse.msu.edu/project-gansvr.html)    |

| [Monocular 3D Object Reconstruction with GAN Inversion](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136610665.pdf) |      Mesh      | ECCV 2022 |        [Project](https://www.mmlab-ntu.com/project/meshinversion/)    |

| [Share With Thy Neighbors: Single-View Reconstruction by Cross-Instance Consistency](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136610282.pdf) |      Mesh      | ECCV 2022 |        [Project](http://imagine.enpc.fr/~monniert/UNICORN/)         |

| [Shape, Pose, and Appearance from a Single Image via Bootstrapped Radiance Field Inversion](https://arxiv.org/abs/2211.11674) |      Implicit      | CVPR 2023 | [Code](https://github.com/google-research/nerf-from-image) |

| [Seeing a Rose in Five Thousand Ways](https://arxiv.org/abs/2212.04965) |      Implicit      | CVPR 2023 | [Project](https://cs.stanford.edu/~yzzhang/projects/rose/) |

| [ShapeClipper: Scalable 3D Shape Learning From Single-View Images via Geometric and CLIP-Based Consistency](https://openaccess.thecvf.com/content/CVPR2023/html/Huang_ShapeClipper_Scalable_3D_Shape_Learning_From_Single-View_Images_via_Geometric_CVPR_2023_paper.html) |      Implicit      | CVPR 2023 | [Project](https://zixuanh.com/projects/shapeclipper.html) |

| [SAOR: Single-View Articulated Object Reconstruction](https://arxiv.org/abs/2303.13514) |      Implicit      | arXiv 2023 | [Project](https://mehmetaygun.github.io/saor) |

| [Progressive Learning of 3D Reconstruction Network from 2D GAN Data](https://arxiv.org/abs/2305.11102) |      Mesh      | arXiv 2023 | [Project](https://research.nvidia.com/labs/adlr/progressive-3d-learning/) |

## Scene-level

### Single-view

|                            Paper                             | Representation | Publisher |                         Project/Code                         |

| :----------------------------------------------------------: | :------------: | :-------: | :----------------------------------------------------------: |

| [IM2CAD](https://openaccess.thecvf.com/content_cvpr_2017/html/Izadinia_IM2CAD_CVPR_2017_paper.html) |      CAD       | CVPR 2017 |         [Code](https://github.com/yyong119/IM2CAD)         |

| [3D-RCNN: Instance-level 3D Object Reconstruction via Render-and-Compare](https://openaccess.thecvf.com/content_cvpr_2018/html/Kundu_3D-RCNN_Instance-Level_3D_CVPR_2018_paper.html) |     Priors     | CVPR 2018 |   [Project](https://abhijitkundu.info/projects/3D-RCNN/)   |

| [Factoring Shape, Pose, and Layout from the 2D Image of a 3D Scene](https://openaccess.thecvf.com/content_cvpr_2018/html/Tulsiani_Factoring_Shape_Pose_CVPR_2018_paper.html) |     Voxel      | CVPR 2018 |     [Project](https://shubhtuls.github.io/factored3d/)     |

| [Holistic 3D Scene Parsing and Reconstruction from a Single RGB Image](https://openaccess.thecvf.com/content_ECCV_2018/html/Siyuan_Huang_Monocular_Scene_Parsing_ECCV_2018_paper.html) |      Mesh       | ECCV 2018 | [Project](https://siyuanhuang.com/holistic_parsing/main.html) |

| [Mesh R-CNN](https://openaccess.thecvf.com/content_ICCV_2019/html/Gkioxari_Mesh_R-CNN_ICCV_2019_paper.html) |      Mesh      | ICCV 2019 |    [Code](https://github.com/facebookresearch/meshrcnn)    |

| [3D Scene Reconstruction With Multi-Layer Depth and Epipolar Transformers](https://openaccess.thecvf.com/content_ICCV_2019/html/Shin_3D_Scene_Reconstruction_With_Multi-Layer_Depth_and_Epipolar_Transformers_ICCV_2019_paper.html) |      Mesh      | ICCV 2019 | [Project](https://research.dshin.org/iccv19/multi-layer-depth) |

| [3D-RelNet: Joint Object and Relational Network for 3D Prediction](https://openaccess.thecvf.com/content_ICCV_2019/html/Kulkarni_3D-RelNet_Joint_Object_and_Relational_Network_for_3D_Prediction_ICCV_2019_paper.html) |     Voxel      | ICCV 2019 |  [Project](https://nileshkulkarni.github.io/relative3d/)   |

| [Total3DUnderstanding: Joint Layout, Object Pose and Mesh Reconstruction for Indoor Scenes from a Single Image](https://openaccess.thecvf.com/content_CVPR_2020/html/Nie_Total3DUnderstanding_Joint_Layout_Object_Pose_and_Mesh_Reconstruction_for_Indoor_CVPR_2020_paper.html) |      Mesh      | CVPR 2020 |       [Project](https://yinyunie.github.io/Total3D/)       |

| [3D Scene Reconstruction from a Single Viewport](https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123670052.pdf) |     Voxel      | ECCV 2020 | [Code](https://github.com/DLR-RM/SingleViewReconstruction) |

| [CoReNet: Coherent 3D scene reconstruction from a single RGB image](https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123470358.pdf) | Voxel+Implicit | ECCV 2020 |     [Code](https://github.com/google-research/corenet)     |

| [Image-to-Voxel Model Translation for 3D Scene Reconstruction and Segmentation](https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123520103.pdf) |     Voxel      | ECCV 2020 |           [Code](https://github.com/vlkniaz/SSZ)           |

| [Holistic 3D Scene Understanding from a Single Image with Implicit Representation](https://arxiv.org/abs/2103.06422) |    Implicit    | CVPR 2021 |  [Project](https://chengzhag.github.io/publication/im3d/)  |

| [From Points to Multi-Object 3D Reconstruction](https://openaccess.thecvf.com/content/CVPR2021/html/Engelmann_From_Points_to_Multi-Object_3D_Reconstruction_CVPR_2021_paper.html) |    Implicit    | CVPR 2021 |  [Project](https://francisengelmann.github.io/points2objects/)  |

| [Learning to Recover 3D Scene Shape from a Single Image](https://openaccess.thecvf.com/content/CVPR2021/html/Yin_Learning_To_Recover_3D_Scene_Shape_From_a_Single_Image_CVPR_2021_paper.html) |    Point Cloud    | CVPR 2021 |  [Code](https://github.com/aim-uofa/AdelaiDepth)  |

| [Patch2CAD: Patchwise Embedding Learning for In-the-Wild Shape Retrieval from a Single Image](https://openaccess.thecvf.com/content/ICCV2021/html/Kuo_Patch2CAD_Patchwise_Embedding_Learning_for_In-the-Wild_Shape_Retrieval_From_a_ICCV_2021_paper.html) |    Mesh    | ICCV 2021 |  /  |

| [Panoptic 3D Scene Reconstruction From a Single RGB Image](https://proceedings.neurips.cc/paper/2021/hash/46031b3d04dc90994ca317a7c55c4289-Abstract.html) |    Voxel    | NIPS 2021 |  [Project](https://manuel-dahnert.com/research/panoptic-reconstruction)  |

| [Voxel-based 3D Detection and Reconstruction of Multiple Objects from a Single Image](https://proceedings.neurips.cc/paper/2021/hash/1415db70fe9ddb119e23e9b2808cde38-Abstract.html) |    Implicit    | NIPS 2021 |  [Project](http://cvlab.cse.msu.edu/project-mdr.html)  |

| [Towards High-Fidelity Single-view Holistic Reconstruction of Indoor Scenes](https://arxiv.org/abs/2207.08656) |    Implicit    | ECCV 2022 |  [Code](https://github.com/UncleMEDM/InstPIFu)  |

| [3D-Former: Monocular Scene Reconstruction with SDF 3D Transformers](https://arxiv.org/abs/2301.13510) |    Implicit    | ICLR 2023 |  [Project](https://weihaosky.github.io/former3d/)  |

| [BUOL: A Bottom-Up Framework With Occupancy-Aware Lifting for Panoptic 3D Scene Reconstruction From a Single Image](https://openaccess.thecvf.com/content/CVPR2023/html/Chu_BUOL_A_Bottom-Up_Framework_With_Occupancy-Aware_Lifting_for_Panoptic_3D_CVPR_2023_paper.html) |    Implicit    | CVPR 2023 |  [Code](https://github.com/chtsy/buol)  |

### Multi-view

|                            Paper                             | Representation | Publisher |                         Project/Code                         |

| :----------------------------------------------------------: | :------------: | :-------: | :----------------------------------------------------------: |

| [MARMVS: Matching Ambiguity Reduced Multiple View Stereo for Efficient Large Scale Scene Reconstruction](https://openaccess.thecvf.com/content_CVPR_2020/html/Xu_MARMVS_Matching_Ambiguity_Reduced_Multiple_View_Stereo_for_Efficient_Large_CVPR_2020_paper.html) | Point Cloud    | CVPR 2020 | / |

| [FroDO: From Detections to 3D Objects](https://openaccess.thecvf.com/content_CVPR_2020/html/Runz_FroDO_From_Detections_to_3D_Objects_CVPR_2020_paper.html) | Implicit | CVPR 2020 | / |

| [Associative3D: Volumetric Reconstruction from Sparse Views](https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123600137.pdf) | Voxel          | ECCV 2020 | [Project](https://jasonqsy.github.io/Associative3D/) |

| [Atlas: End-to-End 3D Scene Reconstruction from Posed Images](https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123520409.pdf) | Mesh           | ECCV 2020 | [Project](http://zak.murez.com/atlas/)               |

| [NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Video](https://arxiv.org/abs/2104.00681) | Mesh           | CVPR 2021 | [Project](https://zju3dv.github.io/neuralrecon/)     |

| [TransformerFusion: Monocular RGB Scene Reconstruction using Transformers](https://proceedings.neurips.cc/paper/2021/hash/0a87257e5308197df43230edf4ad1dae-Abstract.html) |    Implicit    | NIPS 2021 |  [Project](https://aljazbozic.github.io/transformerfusion/)  |

| [Learning 3D Object Shape and Layout without 3D Supervision](https://openaccess.thecvf.com/content/CVPR2022/html/Gkioxari_Learning_3D_Object_Shape_and_Layout_Without_3D_Supervision_CVPR_2022_paper.html) |    Mesh    | CVPR 2022 |  [Project](https://gkioxari.github.io/usl/index.html)  |

| [Directed Ray Distance Functions for 3D Scene Reconstruction](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136620193.pdf) |    Implicit    | ECCV 2022 |  [Project](https://nileshkulkarni.github.io/scene_drdf/)  |

| [Learning 3D Scene Priors with 2D Supervision](https://arxiv.org/abs/2211.14157) |    Mesh    | arXiv 2022 |  [Project](https://yinyunie.github.io/sceneprior-page/)  |

| [FineRecon: Depth-aware Feed-forward Network for Detailed 3D Reconstruction](https://arxiv.org/abs/2304.01480) |    Implicit    | arXiv 2023 |  [Code](https://github.com/apple/ml-finerecon)  |

| [CVRecon: Rethinking 3D Geometric Feature Learning For Neural Reconstruction](https://arxiv.org/abs/2304.14633) |    Implicit    | arXiv 2023 |  [Project](https://cvrecon.ziyue.cool/)  |

| [VisFusion: Visibility-Aware Online 3D Scene Reconstruction From Videos](https://openaccess.thecvf.com/content/CVPR2023/html/Gao_VisFusion_Visibility-Aware_Online_3D_Scene_Reconstruction_From_Videos_CVPR_2023_paper.html) |    Implicit    | CVPR 2023 |  [Project](https://huiyu-gao.github.io/visfusion/)  |

## Neural Surface

### Multi-view

|                            Paper                             | Representation | Publisher |                         Project/Code                         |

| :----------------------------------------------------------: | :------------: | :-------: | :----------------------------------------------------------: |

| [SDFDiff: Differentiable Rendering of Signed Distance Fields for 3D Shape](https://openaccess.thecvf.com/content_CVPR_2020/html/Jiang_SDFDiff_Differentiable_Rendering_of_Signed_Distance_Fields_for_3D_Shape_CVPR_2020_paper.html) |      Implicit      | CVPR 2020 |        [Code](https://yuejiang-nj.github.io/papers/CVPR2020_SDFDiff/project_page.html)         |

| [Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervision](https://openaccess.thecvf.com/content_CVPR_2020/html/Niemeyer_Differentiable_Volumetric_Rendering_Learning_Implicit_3D_Representations_Without_3D_Supervision_CVPR_2020_paper.html) |      Implicit      | CVPR 2020 |        [Code](https://github.com/autonomousvision/differentiable_volumetric_rendering)         |

| [Multiview Neural Surface Reconstruction by Disentangling Geometry and Appearance](https://papers.nips.cc/paper/2020/hash/1a77befc3b608d6ed363567685f70e1e-Abstract.html) |      Implicit      | NIPS 2020 |        [Project](https://lioryariv.github.io/idr/)         |

| [Unsupervised Learning of 3D Object Categories from Videos in the Wild](https://openaccess.thecvf.com/content/CVPR2021/html/Henzler_Unsupervised_Learning_of_3D_Object_Categories_From_Videos_in_the_CVPR_2021_paper.html) |    Implicit    | CVPR 2021 |  [Project](https://henzler.github.io/publication/unsupervised_videos/)  |

| [Neural Lumigraph Rendering](https://openaccess.thecvf.com/content/CVPR2021/html/Kellnhofer_Neural_Lumigraph_Rendering_CVPR_2021_paper.html) |    Implicit    | CVPR 2021 |  [Project](http://www.computationalimaging.org/publications/nlr/)  |

| [Iso-Points: Optimizing Neural Implicit Surfaces With Hybrid Representations](https://openaccess.thecvf.com/content/CVPR2021/html/Yifan_Iso-Points_Optimizing_Neural_Implicit_Surfaces_With_Hybrid_Representations_CVPR_2021_paper.html) |    Implicit    | CVPR 2021 |  [Project](https://yifita.github.io/publication/iso_points/)  |

| [Learning Signed Distance Field for Multi-view Surface Reconstruction](https://openaccess.thecvf.com/content/ICCV2021/html/Zhang_Learning_Signed_Distance_Field_for_Multi-View_Surface_Reconstruction_ICCV_2021_paper.html) |      Implicit      | ICCV 2021 |        [Code](https://github.com/jzhangbs/MVSDF)         |

| [UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstruction](https://openaccess.thecvf.com/content/ICCV2021/html/Oechsle_UNISURF_Unifying_Neural_Implicit_Surfaces_and_Radiance_Fields_for_Multi-View_ICCV_2021_paper.html) |      Implicit      | ICCV 2021 |        [Project](https://moechsle.github.io/unisurf/)         |

| [NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction](https://proceedings.neurips.cc/paper/2021/hash/e41e164f7485ec4a28741a2d0ea41c74-Abstract.html) |      Implicit      | NIPS 2021 |        [Project](https://lingjie0206.github.io/papers/NeuS/)         |

| [NeRS: Neural Reflectance Surfaces for Sparse-View 3D Reconstruction in the Wild](https://proceedings.neurips.cc/paper/2021/hash/f95ec3de395b4bce25b39ef6138da871-Abstract.html) |    Implicit    | NIPS 2021 |  [Project](https://jasonyzhang.com/ners/)  |

| [Volume Rendering of Neural Implicit Surfaces](https://proceedings.neurips.cc/paper/2021/hash/25e2a30f44898b9f3e978b1786dcd85c-Abstract.html) |      Implicit      | ICCV 2021 |        [Unofficial Code](https://github.com/ventusff/neurecon)         |

| [NeuralWarp: Improving neural implicit surfaces geometry with patch warping](https://arxiv.org/abs/2112.09648) |      Implicit      | CVPR 2022 |        [Project](http://imagine.enpc.fr/~darmonf/NeuralWarp/)         |

| [Neural 3D Scene Reconstruction with the Manhattan-world Assumption](https://arxiv.org/abs/2205.02836) |    Implicit    | CVPR 2022 |  [Project](https://zju3dv.github.io/manhattan_sdf/)  |

| [GenDR: A Generalized Differentiable Renderer](https://openaccess.thecvf.com/content/CVPR2022/html/Petersen_GenDR_A_Generalized_Differentiable_Renderer_CVPR_2022_paper.html) |    Mesh    | CVPR 2022 |  [Code](https://github.com/Felix-Petersen/gendr)  |

| [NeRFusion: Fusing Radiance Fields for Large-Scale Scene Reconstruction](https://openaccess.thecvf.com/content/CVPR2022/html/Zhang_NeRFusion_Fusing_Radiance_Fields_for_Large-Scale_Scene_Reconstruction_CVPR_2022_paper.html) |    Implicit    | CVPR 2022 |  [Project](https://jetd1.github.io/NeRFusion-Web/)  |

| [Critical Regularizations for Neural Surface Reconstruction in the Wild](https://openaccess.thecvf.com/content/CVPR2022/html/Zhang_Critical_Regularizations_for_Neural_Surface_Reconstruction_in_the_Wild_CVPR_2022_paper.html) |    Implicit    | CVPR 2022 | / |

| [Multi-View Mesh Reconstruction with Neural Deferred Shading](https://openaccess.thecvf.com/content/CVPR2022/html/Worchel_Multi-View_Mesh_Reconstruction_With_Neural_Deferred_Shading_CVPR_2022_paper.html) |    Mesh    | CVPR 2022 |  [Project](https://fraunhoferhhi.github.io/neural-deferred-shading/)  |

| [Differentiable Stereopsis: Meshes From Multiple Views Using Differentiable Rendering](https://openaccess.thecvf.com/content/CVPR2022/html/Goel_Differentiable_Stereopsis_Meshes_From_Multiple_Views_Using_Differentiable_Rendering_CVPR_2022_paper.html) |    Mesh    | CVPR 2022 |  [Code](https://github.com/shubham-goel/ds)  |

| [SparseNeuS: Fast Generalizable Neural Surface Reconstruction from Sparse views](https://arxiv.org/abs/2206.05737) |    Implicit    | ECCV 2022 |  [Project](https://www.xxlong.site/SparseNeuS/)  |

| [Object-Compositional Neural Implicit Surfaces](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136870194.pdf) |    Implicit    | ECCV 2022 | [Project](https://wuqianyi.top/objectsdf/) |

| [SNeS: Learning Probably Symmetric Neural Surfaces from Incomplete Data](https://arxiv.org/abs/2206.06340) |    Implicit    | ECCV 2022 | [Project](https://www.robots.ox.ac.uk/~vgg/research/snes/) |

| [Neural 3D Reconstruction in the Wild](https://arxiv.org/abs/2205.12955) |    Implicit    | SIGGRAPH 2022 |  [Project](https://zju3dv.github.io/neuralrecon-w/)  |

| [Differentiable Signed Distance Function Rendering](http://rgl.s3.eu-central-1.amazonaws.com/media/papers/Vicini2022sdf_1.pdf) |    Implicit    | SIGGRAPH 2022 |  [Project](http://rgl.epfl.ch/publications/Vicini2022SDF)  |

| [Differentiable Rendering of Neural SDFs through Reparameterization](https://arxiv.org/abs/2206.05344) |    Implicit    | SIGGRAPH Asia 2022 | [Project](https://people.csail.mit.edu/sbangaru/projects/dsdf-2022/index.html) |

| [Learning Consistency-Aware Unsigned Distance Functions Progressively from Raw Point Clouds](https://arxiv.org/abs/2210.02757) |    Implicit    | NIPS 2022 | [Project](https://junshengzhou.github.io/CAP-UDF/) |

| [Geo-Neus: Geometry-Consistent Neural Implicit Surfaces Learning for Multi-view Reconstruction](https://arxiv.org/abs/2205.15848) |    Implicit    | NIPS 2022 |  [Code](https://github.com/GhiXu/Geo-Neus)  |

| [MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstruction](https://arxiv.org/abs/2206.00665) |    Implicit    | NIPS 2022 |  [Project](https://niujinshuchong.github.io/monosdf/)  |

| [HF-NeuS: Improved Surface Reconstruction Using High-Frequency Details](https://arxiv.org/abs/2206.07850) |    Implicit    | NIPS 2022 |  [Project](https://github.com/yiqun-wang/HFS)  |

| [Recovering Fine Details for Neural Implicit Surface Reconstruction](https://openaccess.thecvf.com/content/WACV2023/html/Chen_Recovering_Fine_Details_for_Neural_Implicit_Surface_Reconstruction_WACV_2023_paper.html) |    Implicit    | WACV 2022 |  [Code](https://github.com/fraunhoferhhi/D-NeuS)  |

| [NeuRIS: Neural Reconstruction of Indoor Scenes Using Normal Priors](https://arxiv.org/abs/2206.13597) |    Implicit    | ECCV 2022 |  [Project](https://jiepengwang.github.io/NeuRIS/)  |

| [Sphere-Guided Training of Neural Implicit Surfaces](https://arxiv.org/abs/2209.15511) |    Implicit    | arXiv 2022 | / |

| [QFF: Quantized Fourier Features for Neural Field Representations](https://arxiv.org/abs/2212.00914) |    Implicit    | arXiv 2022 |  /  |

| [NeuS2: Fast Learning of Neural Implicit Surfaces for Multi-view Reconstruction](https://arxiv.org/abs/2212.05231) |    Implicit    | arXiv 2022 |  [Project](https://vcai.mpi-inf.mpg.de/projects/NeuS2/)  |

| [Voxurf: Voxel-based Efficient and Accurate Neural Surface Reconstruction](https://arxiv.org/abs/2208.12697) |    Implicit    | ICLR 2023 | [Code](https://github.com/wutong16/Voxurf) |

| [PermutoSDF: Fast Multi-View Reconstruction with Implicit Surfaces using Permutohedral Lattices](https://arxiv.org/abs/2211.12562) |    Implicit    | CVPR 2023 | [Project](https://radualexandru.github.io/permuto_sdf/) |

| [ShadowNeuS: Neural SDF Reconstruction by Shadow Ray Supervision](https://arxiv.org/abs/2211.14086) |    Implicit    | CVPR 2023 |  [Project](https://gerwang.github.io/shadowneus/)  |

| [NeuralUDF: Learning Unsigned Distance Fields for Multi-view Reconstruction of Surfaces with Arbitrary Topologies](https://arxiv.org/abs/2211.14173) |    Implicit    | CVPR 2023 |  [Project](https://www.xxlong.site/NeuralUDF/)  |

| [NeuDA: Neural Deformable Anchor for High-Fidelity Implicit Surface Reconstruction](https://arxiv.org/abs/2303.02375) |     Implicit      | CVPR 2023 | [Project](https://3d-front-future.github.io/neuda/) |

| [SparseFusion: Distilling View-conditioned Diffusion for 3D Reconstruction](https://arxiv.org/abs/2212.00792) |    Implicit    | CVPR 2023 |  [Project](https://sparsefusion.github.io/)  |

| [I$^2$-SDF: Intrinsic Indoor Scene Reconstruction and Editing via Raytracing in Neural SDFs](https://arxiv.org/abs/2303.07634) |     Implicit      | CVPR 2023 | [Project](https://jingsenzhu.github.io/i2-sdf/) |

| [NeAT: Learning Neural Implicit Surfaces with Arbitrary Topologies from Multi-view Images](https://arxiv.org/abs/2303.12012) |     Implicit      | CVPR 2023 | [Project](https://xmeng525.github.io/xiaoxumeng.github.io/projects/cvpr23_neat) |

| [NeUDF: Leaning Neural Unsigned Distance Fields With Volume Rendering](https://openaccess.thecvf.com/content/CVPR2023/html/Liu_NeUDF_Leaning_Neural_Unsigned_Distance_Fields_With_Volume_Rendering_CVPR_2023_paper.html) |     Implicit      | CVPR 2023 | [Project](http://geometrylearning.com/neudf/) |

| [Towards Better Gradient Consistency for Neural Signed Distance Functions via Level Set Alignment](https://openaccess.thecvf.com/content/CVPR2023/html/Ma_Towards_Better_Gradient_Consistency_for_Neural_Signed_Distance_Functions_via_CVPR_2023_paper.html) |     Implicit      | CVPR 2023 | [Code](https://github.com/mabaorui/TowardsBetterGradient/) |

| [Neuralangelo: High-Fidelity Neural Surface Reconstruction](https://openaccess.thecvf.com/content/CVPR2023/html/Li_Neuralangelo_High-Fidelity_Neural_Surface_Reconstruction_CVPR_2023_paper.html) |     Implicit      | CVPR 2023 | [Project](https://research.nvidia.com/labs/dir/neuralangelo/) |

| [VolRecon: Volume Rendering of Signed Ray Distance Functions for Generalizable Multi-View Reconstruction](https://openaccess.thecvf.com/content/CVPR2023/html/Ren_VolRecon_Volume_Rendering_of_Signed_Ray_Distance_Functions_for_Generalizable_CVPR_2023_paper.html) |     Implicit      | CVPR 2023 | [Project](https://fangjinhuawang.github.io/VolRecon/) |

| [PET-NeuS: Positional Encoding Tri-Planes for Neural Surfaces](https://openaccess.thecvf.com/content/CVPR2023/html/Wang_PET-NeuS_Positional_Encoding_Tri-Planes_for_Neural_Surfaces_CVPR_2023_paper.html) |     Implicit      | CVPR 2023 | / |

| [HR-NeuS: Recovering High-Frequency Surface Geometry via Neural Implicit Surfaces](https://arxiv.org/abs/2302.06793) |    Implicit    | arXiv 2023 | / |

| [RICO: Regularizing the Unobservable for Indoor Compositional Reconstruction](https://arxiv.org/abs/2303.08605) |    Implicit    | arXiv 2023 | / |

| [Learning a Room with the Occ-SDF Hybrid: Signed Distance Function Mingled with Occupancy Aids Scene Representation](https://arxiv.org/abs/2303.09152) |    Implicit    | arXiv 2023 | / |

| [NeUDF: Learning Unsigned Distance Fields from Multi-view Images for Reconstructing Non-watertight Models](https://arxiv.org/abs/2303.15368) |     Implicit      | arXiv 2023 | / |

| [S-VolSDF: Sparse Multi-View Stereo Regularization of Neural Implicit](https://arxiv.org/abs/2303.17712) |     Implicit      | arXiv 2023 | [Project](https://hao-yu-wu.github.io/s-volsdf/) |

| [VDN-NeRF: Resolving Shape-Radiance Ambiguity via View-Dependence Normalization](https://arxiv.org/abs/2303.17968) |     Implicit      | arXiv 2023 | / |

| [FastMESH: Fast Surface Reconstruction by Hexagonal Mesh-based Neural Rendering](https://arxiv.org/abs/2305.17858) |     Mesh      | arXiv 2023 | / |

| [Explicit Neural Surfaces: Learning Continuous Geometry With Deformation Fields](https://arxiv.org/abs/2306.02956) |     Implicit      | arXiv 2023 | / |

### Point-cloud

|                            Paper                             | Representation | Publisher |                         Project/Code                         |

| :----------------------------------------------------------: | :------------: | :-------: | :----------------------------------------------------------: |

| [Deep Geometric Prior for Surface Reconstruction](https://openaccess.thecvf.com/content_CVPR_2019/html/Williams_Deep_Geometric_Prior_for_Surface_Reconstruction_CVPR_2019_paper.html) |     Patches      | CVPR 2019 |        [Code](https://github.com/fwilliams/deep-geometric-prior)        |

| [Scan2Mesh: From Unstructured Range Scans to 3D Meshes](https://openaccess.thecvf.com/content_CVPR_2019/html/Dai_Scan2Mesh_From_Unstructured_Range_Scans_to_3D_Meshes_CVPR_2019_paper.html) |     Mesh      | CVPR 2019 | [Code](https://github.com/mohamed-ebbed/Scan2Mesh) |

| [Meshlet Priors for 3D Mesh Reconstruction](https://openaccess.thecvf.com/content_CVPR_2020/html/Badki_Meshlet_Priors_for_3D_Mesh_Reconstruction_CVPR_2020_paper.html) |     Mesh      | CVPR 2020 | [Code](https://github.com/NVlabs/meshlets) |

| [SSRNet: Scalable 3D Surface Reconstruction Network](https://openaccess.thecvf.com/content_CVPR_2020/html/Mi_SSRNet_Scalable_3D_Surface_Reconstruction_Network_CVPR_2020_paper.html) |     Implicit      | CVPR 2020 | / |

| [SAL: Sign Agnostic Learning of Shapes from Raw Data](http://openaccess.thecvf.com/content_CVPR_2020/html/Atzmon_SAL_Sign_Agnostic_Learning_of_Shapes_From_Raw_Data_CVPR_2020_paper.html) |     Implicit      | CVPR 2020 |        [Code](https://github.com/matanatz/SAL)      |

| [Implicit Geometric Regularization for Learning Shapes](https://proceedings.mlr.press/v119/gropp20a.html) |     Implicit      | ICML 2020 |        [Code](https://github.com/amosgropp/IGR)        |

| [Meshing Point Clouds with Predicted Intrinsic-Extrinsic Ratio Guidance](https://arxiv.org/abs/2007.09267) |     Mesh      | ECCV 2020 |        [Code](https://github.com/Colin97/Point2Mesh)        |

| [PointTriNet: Learned Triangulation of 3D Point Sets](https://arxiv.org/abs/2005.02138) |     Mesh      | ECCV 2020 |        [Code](https://github.com/nmwsharp/learned-triangulation)      |

| [Points2Surf: Learning Implicit Surfaces from Point Cloud Patches](https://arxiv.org/abs/2007.10453) |     Implicit      | ECCV 2020 |        [Code](https://github.com/ErlerPhilipp/points2surf)      |

| [Convolutional Occupancy Networks](https://arxiv.org/abs/2003.04618) |     Implicit      | ECCV 2020 |        [Code](https://github.com/autonomousvision/convolutional_occupancy_networks)      |

| [Implicit Neural Representations with Periodic Activation Functions](https://proceedings.neurips.cc/paper/2020/hash/53c04118df112c13a8c34b38343b9c10-Abstract.html) |     Implicit      | NIPS 2020 |        [Project](https://www.vincentsitzmann.com/siren/)      |

| [Neural Unsigned Distance Fields for Implicit Function Learning](https://proceedings.neurips.cc/paper/2020/hash/f69e505b08403ad2298b9f262659929a-Abstract.html) |     Implicit      | NIPS 2020 |        [Code](https://github.com/jchibane/ndf)        |

| [Differentiable Surface Triangulation](https://arxiv.org/abs/2109.10695) |     Mesh      | TOG 2021 |        [Code](https://github.com/mrakotosaon/diff-surface-triangulation)      |

| [SALD: Sign Agnostic Learning with Derivatives](https://arxiv.org/abs/2006.05400) |     Implicit      | ICLR 2021 |        [Code](https://github.com/matanatz/SALD)      |

| [Deep Implicit Moving Least-Squares Functions for 3D Reconstruction](https://openaccess.thecvf.com/content/CVPR2021/html/Liu_Deep_Implicit_Moving_Least-Squares_Functions_for_3D_Reconstruction_CVPR_2021_paper.html) |     Implicit      | CVPR 2021 |        [Code](https://github.com/Andy97/DeepMLS)      |

| [Sign-Agnostic Implicit Learning of Surface Self-Similarities for Shape Modeling and Reconstruction from Raw Point Clouds](https://openaccess.thecvf.com/content/CVPR2021/html/Zhao_Sign-Agnostic_Implicit_Learning_of_Surface_Self-Similarities_for_Shape_Modeling_and_CVPR_2021_paper.html) |     Implicit      | CVPR 2021 | / |

| [Learning Delaunay Surface Elements for Mesh Reconstruction](https://openaccess.thecvf.com/content/CVPR2021/html/Rakotosaona_Learning_Delaunay_Surface_Elements_for_Mesh_Reconstruction_CVPR_2021_paper.html) |     Mesh      | CVPR 2021 |        [Code](https://github.com/mrakotosaon/dse-meshing)        |

| [Neural Splines: Fitting 3D Surfaces with Infinitely-Wide Neural Networks](https://openaccess.thecvf.com/content/CVPR2021/html/Williams_Neural_Splines_Fitting_3D_Surfaces_With_Infinitely-Wide_Neural_Networks_CVPR_2021_paper.html) |     Implicit      | CVPR 2021 |        [Code](https://github.com/fwilliams/neural-splines)      |

| [Neural-Pull: Learning Signed Distance Functions from Point Clouds by Learning to Pull Space onto Surfaces](https://proceedings.mlr.press/v139/ma21b.html) |     Implicit      | ICML 2021 |        [Code](https://github.com/mabaorui/NeuralPull)      |

| [Phase Transitions, Distance Functions, and Implicit Neural Representations](https://arxiv.org/abs/2106.07689) |     Implicit      | ICML 2021 | / |

| [Vis2Mesh: Efficient Mesh Reconstruction from Unstructured Point Clouds of Large Scenes with Learned Virtual View Visibility](https://openaccess.thecvf.com/content/ICCV2021/papers/Song_Vis2Mesh_Efficient_Mesh_Reconstruction_From_Unstructured_Point_Clouds_of_Large_ICCV_2021_paper.pdf) |     Mesh      | ICCV 2021 |        [Code](https://github.com/GDAOSU/vis2mesh)      |

| [Deep Hybrid Self-Prior for Full 3D Mesh Generation](https://openaccess.thecvf.com/content/ICCV2021/html/Wei_Deep_Hybrid_Self-Prior_for_Full_3D_Mesh_Generation_ICCV_2021_paper.html) |     Mesh      | ICCV 2021 | [Project](https://yqdch.github.io/DHSP3D/) |

| [Adaptive Surface Reconstruction with Multiscale Convolutional Kernels](https://openaccess.thecvf.com/content/ICCV2021/papers/Ummenhofer_Adaptive_Surface_Reconstruction_With_Multiscale_Convolutional_Kernels_ICCV_2021_paper.pdf) |     Mesh      | ICCV 2021 |        [Code](https://github.com/isl-org/adaptive-surface-reconstruction)      |

| [SA-ConvONet: Sign-Agnostic Optimization of Convolutional Occupancy Networks](http://openaccess.thecvf.com/content/ICCV2021/html/Tang_SA-ConvONet_Sign-Agnostic_Optimization_of_Convolutional_Occupancy_Networks_ICCV_2021_paper.html) |     Implicit      | ICCV 2021 |        [Code](https://github.com/tangjiapeng/SA-ConvONet)      |

| [Deep Implicit Surface Point Prediction Networks](http://openaccess.thecvf.com/content/ICCV2021/html/Venkatesh_Deep_Implicit_Surface_Point_Prediction_Networks_ICCV_2021_paper.html) |     Implicit      | ICCV 2021 |        [Project](https://sites.google.com/view/cspnet)      |

| [Shape As Points: A Differentiable Poisson Solver](https://arxiv.org/abs/2106.03452) |     Mesh      | NIPS 2021 |        [Project](https://pengsongyou.github.io/sap)      |

| [AIR-Nets: An Attention-Based Framework for Locally Conditioned Implicit Representations](https://arxiv.org/abs/2110.11860) |     Implicit      | 3DV 2021 |     [Code](https://github.com/SimonGiebenhain/AIR-Nets)    |

| [Scalable Surface Reconstruction with Delaunay-Graph Neural Networks](https://arxiv.org/abs/2107.06130) |     Mesh      | SGP 2021 | [Code](https://github.com/raphaelsulzer/dgnn) |

| [Neural-IMLS: Learning Implicit Moving Least-Squares for Surface Reconstruction from Unoriented Point clouds](https://arxiv.org/abs/2109.04398) |     Implicit      | arXiv 2021 |        [Project](https://qiujiedong.github.io/publications/Neural_IMLS/)      |

| [Neural Fields as Learnable Kernels for 3D Reconstruction](https://arxiv.org/abs/2111.13674) |     Implicit      | CVPR 2022 |        [Project](https://nv-tlabs.github.io/nkf/)      |

| [POCO: Point Convolution for Surface Reconstruction](https://arxiv.org/abs/2201.01831) |     Implicit      | CVPR 2022 |     [Code](https://github.com/valeoai/POCO)    |

| [GIFS: Neural Implicit Function for General Shape Representation](https://arxiv.org/abs/2204.07126) |     Implicit      | CVPR 2022 |     [Project](https://jianglongye.com/gifs/)    |

| [Reconstructing Surfaces for Sparse Point Clouds with On-Surface Priors](https://arxiv.org/abs/2204.10603) |     Implicit      | CVPR 2022 |     [Code](https://github.com/mabaorui/OnSurfacePrior)    |

| [Surface Reconstruction from Point Clouds by Learning Predictive Context Priors](https://arxiv.org/abs/2204.11015) |     Implicit      | CVPR 2022 |     [Code](https://github.com/mabaorui/predictablecontextprior)    |

| [DiGS: Divergence Guided Shape Implicit Neural Representation for Unoriented Point Clouds](https://openaccess.thecvf.com/content/CVPR2022/html/Ben-Shabat_DiGS_Divergence_Guided_Shape_Implicit_Neural_Representation_for_Unoriented_Point_CVPR_2022_paper.html) |     Implicit      | CVPR 2022 |     [Project](https://chumbyte.github.io/DiGS-Site/)    |

| [VisCo Grids: Surface Reconstruction with Viscosity and Coarea Grids](https://arxiv.org/abs/2303.14569) |     Implicit      | NIPS 2022 | / |

| [GenSDF: Two-Stage Learning of Generalizable Signed Distance Functions](https://arxiv.org/abs/2206.02780) |     Implicit      | NIPS 2022 | [Project](https://light.princeton.edu/publication/gensdf/) |

| [Dual Octree Graph Networks for Learning Adaptive Volumetric Shape Representations](https://arxiv.org/abs/2205.02825) |     Implicit      | SIGGRAPH 2022 | [Code](https://github.com/microsoft/DualOctreeGNN) |

| [Deep Point Cloud Simplification for High-quality Surface Reconstruction](https://arxiv.org/abs/2203.09088) |     Implicit      | arXiv 2022 | / |

| [RangeUDF: Semantic Surface Reconstruction from 3D Point Clouds](https://arxiv.org/abs/2204.09138) |     Implicit      | arXiv 2022 | [Code](https://github.com/vlar-group/rangeudf) |

| [Neural Poisson: Indicator Functions for Neural Fields](https://arxiv.org/abs/2211.14249) |     Implicit      | arXiv 2022 | / |

| [GeoUDF: Surface Reconstruction from 3D Point Clouds via Geometry-guided Distance Representation](https://arxiv.org/abs/2211.16762) |     Implicit      | arXiv 2022 | [Code](https://github.com/rsy6318/GeoUDF) |

| [CircNet: Meshing 3D Point Clouds with Circumcenter Detection](https://arxiv.org/abs/2301.09253) |     Mesh      | ICLR 2023 | / |

| [ALTO: Alternating Latent Topologies for Implicit 3D Reconstruction](https://arxiv.org/abs/2212.04096) |     Implicit      | CVPR 2023 | [Project](http://visual.ee.ucla.edu/alto.htm/) |

| [Octree Guided Unoriented Surface Reconstruction](https://openaccess.thecvf.com/content/CVPR2023/html/Koneputugodage_Octree_Guided_Unoriented_Surface_Reconstruction_CVPR_2023_paper.html) |     Implicit      | CVPR 2023 | [Project](https://chumbyte.github.io/OG-INR-Site/) |

| [Unsupervised Inference of Signed Distance Functions From Single Sparse Point Clouds Without Learning Priors](https://openaccess.thecvf.com/content/CVPR2023/html/Chen_Unsupervised_Inference_of_Signed_Distance_Functions_From_Single_Sparse_Point_CVPR_2023_paper.html) |     Implicit      | CVPR 2023 | [Code](https://github.com/chenchao15/NeuralTPS) |

| [Neural Vector Fields: Implicit Representation by Explicit Learning](https://openaccess.thecvf.com/content/CVPR2023/html/Yang_Neural_Vector_Fields_Implicit_Representation_by_Explicit_Learning_CVPR_2023_paper.html) |     Implicit      | CVPR 2023 | [Code](https://github.com/Wi-sc/NVF) |

| [StEik: Stabilizing the Optimization of Neural Signed Distance Functions and Finer Shape Representation](https://arxiv.org/abs/2305.18414) |     Implicit      | arXiv 2023 | / |

| [Learning Signed Distance Functions from Noisy 3D Point Clouds via Noise to Noise Mapping](https://arxiv.org/abs/2306.01405) |     Implicit      | ICML 2023 | [Project](https://github.com/mabaorui/Noise2NoiseMapping/) |

### RGB-D

|                            Paper                             | Representation | Publisher |                         Project/Code                         |

| :----------------------------------------------------------: | :------------: | :-------: | :----------------------------------------------------------: |

| [Neural RGB-D Surface Reconstruction](https://openaccess.thecvf.com/content/CVPR2022/html/Azinovic_Neural_RGB-D_Surface_Reconstruction_CVPR_2022_paper.html) |     Implicit      | CVPR 2022 |        [Project](https://dazinovic.github.io/neural-rgbd-surface-reconstruction/)        |

| [BNV-Fusion: Dense 3D Reconstruction Using Bi-Level Neural Volume Fusion](https://openaccess.thecvf.com/content/CVPR2022/html/Li_BNV-Fusion_Dense_3D_Reconstruction_Using_Bi-Level_Neural_Volume_Fusion_CVPR_2022_paper.html) |     Implicit      | CVPR 2022 |        [Code](https://github.com/likojack/bnv_fusion)        |

| [NICE-SLAM: Neural Implicit Scalable Encoding for SLAM](https://openaccess.thecvf.com/content/CVPR2022/html/Zhu_NICE-SLAM_Neural_Implicit_Scalable_Encoding_for_SLAM_CVPR_2022_paper.html) |     Implicit      | CVPR 2022 |   [Project](https://pengsongyou.github.io/nice-slam)   |

| [ShAPO: Implicit Representations for Multi-Object Shape, Appearance, and Pose Optimization](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136620266.pdf) |     Implicit      | ECCV 2022 |        [Project](https://zubair-irshad.github.io/projects/ShAPO.html)        |

| [CIRCLE: Convolutional Implicit Reconstruction and Completion for Large-scale Indoor Scene](https://www.ecva.net/papers/eccv_2022/papers_ECCV/html/4658_ECCV_2022_paper.php) |     Implicit      | ECCV 2022 |        [Code](https://github.com/otakuxiang/circle)        |

| [Neural Surface Reconstruction of Dynamic Scenes with Monocular RGB-D Camera](https://arxiv.org/abs/2206.15258) |     Implicit      | NIPS 2022 |        [Project](https://ustc3dv.github.io/ndr/)        |

| [GO-Surf: Neural Feature Grid Optimization for Fast, High-Fidelity RGB-D Surface Reconstruction](https://arxiv.org/abs/2206.14735) |     Implicit      | 3DV 2022 |        [Project](https://jingwenwang95.github.io/go_surf/)        |

| [FastSurf: Fast Neural RGB-D Surface Reconstruction using Per-Frame Intrinsic Refinement and TSDF Fusion Prior Learning](https://arxiv.org/abs/2303.04508) |     Implicit      | arXiv 2023 |        [Project](https://rokit-healthcare.github.io/FastSurf/)        |

| [Dynamic Voxel Grid Optimization for High-Fidelity RGB-D Supervised Surface Reconstruction](https://arxiv.org/abs/2304.06178) |     Implicit      | arXiv 2023 |        /        |

| [Multiview Compressive Coding for 3D Reconstruction](https://arxiv.org/abs/2301.08247) |     Implicit      | CVPR 2023 |        [Project](https://mcc3d.github.io/)        |

| [MobileBrick: Building LEGO for 3D Reconstruction on Mobile Devices](https://arxiv.org/abs/2303.01932) |     Implicit      | CVPR 2023 |        [Project](https://code.active.vision/MobileBrick/)        |

| [TMO: Textured Mesh Acquisition of Objects with a Mobile Device by using Differentiable Rendering](https://arxiv.org/abs/2303.15060) |     Mesh      | CVPR 2023 |        [Project](https://jh-choi.github.io/TMO/)        |

## Survey

|                            Paper                             | Publisher  |

| :--------------------------------------------------------------------: | :--------: |

| [Image-based 3D Object Reconstruction: State-of-the-Art and Trends in the Deep Learning Era](https://arxiv.org/abs/1906.06543) | TPAMI 2019 |

| [Neural Fields in Visual Computing and Beyond](https://arxiv.org/abs/2111.11426) | arXiv 2021 |

| [Advances in Neural Rendering](https://arxiv.org/abs/2111.05849) | EUROGRAPHICS 2022 |

| [Surface Reconstruction from Point Clouds: A Survey and a Benchmark](https://arxiv.org/abs/2205.02413) | arXiv 2022 |

| [NeRF: Neural Radiance Field in 3D Vision, A Comprehensive Review](https://arxiv.org/abs/2210.00379) | arXiv 2022 |

| [A Review of Deep Learning-Powered Mesh Reconstruction Methods](https://arxiv.org/abs/2303.02879) | arXiv 2023 |