Ecosyste.ms: Awesome

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

Awesome Lists | Featured Topics | Projects

https://github.com/DynaVis/awesome-dynamic-scene-reconstruction

A curated list of awesome neural scene reconstruction datasets and papers, inspired by awesome-computer-vision.
https://github.com/DynaVis/awesome-dynamic-scene-reconstruction

List: awesome-dynamic-scene-reconstruction

Last synced: 3 months ago
JSON representation

A curated list of awesome neural scene reconstruction datasets and papers, inspired by awesome-computer-vision.

Host: GitHub
URL: https://github.com/DynaVis/awesome-dynamic-scene-reconstruction
Owner: DynaVis
License: mit
Created: 2023-06-19T15:16:32.000Z (over 1 year ago)
Default Branch: main
Last Pushed: 2023-06-21T21:05:43.000Z (over 1 year ago)
Last Synced: 2024-04-10T17:19:04.338Z (7 months ago)
Size: 41 KB
Stars: 1
Watchers: 5
Forks: 0
Open Issues: 0
Metadata Files:
- Readme: README.md
- License: LICENSE

Awesome Lists containing this project

ultimate-awesome - awesome-dynamic-scene-reconstruction - A curated list of awesome neural scene reconstruction datasets and papers, inspired by awesome-computer-vision. (Other Lists / PowerShell Lists)

README

        # Awesome Dynamic Scene Reconstruction [![Awesome](https://cdn.rawgit.com/sindresorhus/awesome/d7305f38d29fed78fa85652e3a63e154dd8e8829/media/badge.svg)](https://github.com/sindresorhus/awesome)

A curated list of awesome dynamic scene reconstruction papers and datasets, inspired by [awesome-computer-vision](https://github.com/jbhuang0604/awesome-computer-vision).

## Contribute 

To contribute to this list, please submit a pull request and edit README.md with a table entry in the following format:


| [Paper title](paper url) | venue acronym and year | [project](project url) <br> [code](code url) <br> [data](data url) |

## Papers 

Papers are organised into two categories, "General Scenes" and "Human-centric", with links to paper, project, code and datasets where available.

### General Scenes

|Title|Venue|Links|

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

|[DynIBaR Neural Dynamic Image-Based Rendering](https://arxiv.org/abs/2211.11082) | CVPR 2023| [project](https://dynibar.github.io/)
[code](https://github.com/google/dynibar)|

|[DynamicStereo: Consistent Dynamic Depth from Stereo Videos](https://arxiv.org/abs/2305.02296) | CVPR 2023 | [project](https://dynamic-stereo.github.io/) 
 [code](https://github.com/facebookresearch/dynamic_stereo)|

|[Temporal Interpolation Is All You Need for Dynamic Neural Radiance Fields](https://arxiv.org/abs/2302.09311)| CVPR 2023 | [project](https://sungheonpark.github.io/tempinterpnerf/) |

|[HexPlane: A Fast Representation for Dynamic Scenes](https://arxiv.org/abs/2301.09632)| CVPR 2023 | [project](https://caoang327.github.io/HexPlane/) 
 [code](https://github.com/Caoang327/HexPlane) |

|[NeRF-DS: Neural Radiance Fields for Dynamic Specular Objects](https://arxiv.org/abs/2303.14435)|CVPR 2023 | [project](https://jokeryan.github.io/projects/nerf-ds/) 
 [code](https://github.com/JokerYan/NeRF-DS) 
 [data](https://github.com/JokerYan/NeRF-DS/releases/tag/v0.1-pre-release) | 

|[RoDynRF:Robust Dynamic Radiance Fields](https://arxiv.org/abs/2301.02239)| CVPR 2023| [project](https://robust-dynrf.github.io/?ref=dataphoenix.info)|

|[DyLiN: Making Light Field Networks Dynamic](https://arxiv.org/abs/2303.14243)| CVPR 2023 | [project](https://dylin2023.github.io/) 
 [code](https://github.com/Heng14/DyLiN) | 

|[Neural 3D Video Synthesis from Multi-view Video](https://arxiv.org/abs/2103.02597)| CVPR 2022 | [project](https://neural-3d-video.github.io/) 
 [data](https://github.com/facebookresearch/Neural_3D_Video) |

|[OcclusionFusion: Occlusion-aware Motion Estimation for Real-time Dynamic 3D Reconstruction](https://arxiv.org/abs/2203.07977) | CVPR 2022 | [project](https://wenbin-lin.github.io/OcclusionFusion/) 
 [code](https://github.com/wenbin-lin/OcclusionFusion/) | 

|[DeepDeform: Learning Non-rigid RGB-D Reconstruction with Semi-supervised Data](https://arxiv.org/abs/1912.04302)| CVPR 2020 | [project](https://niessnerlab.org/projects/bozic2020deepdeform.html) 
 [data](https://github.com/AljazBozic/DeepDeform)|

|[Hybrid Modeling of Non-Rigid Scenes From RGBD Cameras](https://ieeexplore.ieee.org/document/8425011)| TCSVT 2019 | [project](https://cvssp.org/projects/4d/dynamic_rgbd_modelling/) 
 [data](https://cvssp.org/projects/4d/dynamic_rgbd_modelling/) |

|[General Dynamic Scene Reconstruction from Multiple View Video](https://openaccess.thecvf.com/content_iccv_2015/papers/Mustafa_General_Dynamic_Scene_ICCV_2015_paper.pdf)| ICCV 2015 |[project](https://cvssp.org/projects/4DMP/DyRecon/) 
 [data](https://cvssp.org/data/cvssp3d/)|

|[Monocular 3D Reconstruction of Locally Textured Surfaces](https://ieeexplore.ieee.org/document/6186734)| PAMI 2012| [data](https://www.epfl.ch/labs/cvlab/data/data-dsr-index-php/)|

|[3D Reconstruction of Dynamic Scenes with Multiple Handheld Cameras](https://link.springer.com/chapter/10.1007/978-3-642-33709-3_43)| ECCV 2012| - |

|[Multi-view Occlusion Reasoning for Probabilistic Silhouette-Based Dynamic Scene Reconstruction](http://vision.cse.psu.edu/research/3Dreconstruction/relatedWork/papers/GuanAndPollefeys_SilhouetteBased.pdf)| IJCV 2010 | - |

### Human-centric

|Title|Venue|Links|

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

|[HumanRF: High-Fidelity Neural Radiance Fields for Humans in Motion](https://arxiv.org/abs/2305.06356)| SIGGRAPH 2023 | [project](https://synthesiaresearch.github.io/humanrf/) 
 [code](https://github.com/synthesiaresearch/humanrf) 
 [data](https://www.actors-hq.com/)|

|[BEDLAM: A Synthetic Dataset of Bodies Exhibiting Detailed Lifelike Animated Motion](https://bedlam.is.tuebingen.mpg.de/media/upload/BEDLAM_CVPR2023.pdf)| CVPR 2023 | [project](https://bedlam.is.tue.mpg.de/) 
 [code](https://github.com/pixelite1201/BEDLAM) 
 [data](https://bedlam.is.tue.mpg.de/#data)|

|[Learning Neural Volumetric Representations of Dynamic Humans in Minutes](https://openaccess.thecvf.com/content/CVPR2023/papers/Geng_Learning_Neural_Volumetric_Representations_of_Dynamic_Humans_in_Minutes_CVPR_2023_paper.pdf) | CVPR 2023 | [project](https://zju3dv.github.io/instant_nvr/) 
 [code](https://github.com/zju3dv/instant-nvr/) 
 [data](https://github.com/zju3dv/instant-nvr/blob/master/docs/install.md#set-up-datasets)|

|[Tensor4D : Efficient Neural 4D Decomposition for High-fidelity Dynamic Reconstruction and Rendering](https://arxiv.org/abs/2211.11610)| CVPR 2023 | [project](https://liuyebin.com/tensor4d/tensor4d.html) 
 [code](https://github.com/DSaurus/Tensor4D) 
 [data](https://mailstsinghuaeducn-my.sharepoint.com/:f:/g/personal/shaorz20_mails_tsinghua_edu_cn/EsNxn0pJ19lFrRMKAS1YDx0Bv_V9LAdub9jnYvT40QZEDA?e=ChbsFX)|

|[Representing Volumetric Videos as Dynamic MLP Maps](https://arxiv.org/abs/2304.06717)| CVPR 2023 | [project](https://zju3dv.github.io/mlp_maps/) 
 [code](https://github.com/zju3dv/mlp_maps) 
 [data](https://github.com/zju3dv/mlp_maps/blob/master/INSTALL.md)|

|[Function4D: Real-time Human Volumetric Capture from Very Sparse Consumer RGBD Sensors](https://arxiv.org/abs/2105.01859)| CVPR 2021 | [project](http://www.liuyebin.com/Function4D/Function4D.html) 
 [data](https://github.com/ytrock/THuman2.0-Dataset)|

|[SIZER: A Dataset and Model for Parsing 3D Clothing and Learning Size Sensitive 3D Clothing](https://arxiv.org/abs/2007.11610)| ECCV 2020 | [project](https://virtualhumans.mpi-inf.mpg.de/sizer/) 
 [code](https://github.com/garvita-tiwari/sizer) 
 [data](https://nextcloud.mpi-klsb.mpg.de/index.php/s/nx6wK6BJFZCTF8C/authenticate/showShare) | 

|[DeepHuman: 3D Human Reconstruction from a Single Image](https://openaccess.thecvf.com/content_ICCV_2019/papers/Zheng_DeepHuman_3D_Human_Reconstruction_From_a_Single_Image_ICCV_2019_paper.pdf)| ICCV 2019 | [project](http://www.liuyebin.com/deephuman/deephuman.html) 
 [data](http://www.liuyebin.com/deephuman/deephuman.html) |

|[3DPeople: Modeling the Geometry of Dressed Humans](https://arxiv.org/abs/1904.04571)| ICCV 2019 | [project](https://www.albertpumarola.com/research/3DPeople/index.html) 
 [data](https://cv.iri.upc-csic.es/) |

|[Dynamic FAUST: Registering Human Bodies in Motion](https://ieeexplore.ieee.org/document/8100074)| CVPR 2017 | [project](https://is.mpg.de/publications/dfaust-cvpr-2017)  
 [data](https://dfaust.is.tue.mpg.de/)|

|[Learning from Synthetic Humans](https://arxiv.org/abs/1701.01370)| CVPR 2017| [project](https://www.di.ens.fr/willow/research/surreal/) 
 [code](https://github.com/gulvarol/surreal) 
 [data](https://www.di.ens.fr/willow/research/surreal/data/) |

|[Unstructured Video-Based Rendering: Interactive Exploration of Casually Captured Videos](https://dl.acm.org/doi/10.1145/1778765.1778824) | SIGGRAPH 2010 | [data](https://cvg.ethz.ch/research/unstructured-vbr/) |

|[Articulated Mesh Animation from Multi-view Silhouettes](http://people.csail.mit.edu/drdaniel/research/vlasic-2008-ama.pdf) | ToG 2008 | [project](http://people.csail.mit.edu/drdaniel/mesh_animation/) 
 [data](http://people.csail.mit.edu/drdaniel/mesh_animation/#data)|

## Dataset Repositories

A list of larger dataset repos that are used for multiple works.

|Title|

|-----|

|[4D Repository](https://kinovis.inria.fr/4d-repository/)|

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