Science Score: 44.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
✓CITATION.cff file
Found CITATION.cff file -
✓codemeta.json file
Found codemeta.json file -
✓.zenodo.json file
Found .zenodo.json file -
○DOI references
-
○Academic publication links
-
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (11.5%) to scientific vocabulary
Keywords
Repository
A framework for 4D reconstruction from monocular videos.
Basic Info
- Host: GitHub
- Owner: lab4d-org
- License: mit
- Language: Python
- Default Branch: main
- Homepage: https://lab4d-org.github.io/lab4d/
- Size: 69.7 MB
Statistics
- Stars: 305
- Watchers: 15
- Forks: 20
- Open Issues: 6
- Releases: 0
Topics
Metadata Files
README.md
Lab4D
[Docs & Tutorials] [Data & Checkpoints]
This is an alpha release and the APIs are subject to change. Please provide feedback and report bugs via github issues. Thank you for your support.
About
Lab4D is a framework for 4D reconstruction from monocular videos. The software is licensed under the MIT license.
TODOs
- [ ] web viewer (see PPR branch)
- [ ] evaluation (see PPR branch) and benchmarks
- [ ] multi-view reconstruction
- [ ] feedforward models (see DASR)
Acknowledgement
- Our pre-processing pipeline is built upon the following open-sourced repos:
- Segmentation: Track-Anything, Grounding-DINO
- Feature & correspondence: DensePose-CSE, DINOv2, VCNPlus
- Depth: ZoeDepth
- Camera: BANMo-viewpoint
- We use dqtorch for efficient rotation operations
- We thank @mjlbach, @alexanderbergman7, and @terrancewang for testing and feedback
- We thank @jasonyzhang, @MightyChaos, @JudyYe, and @andrewsonga for feedback
If you use this project for your research, please consider citing the following papers.
For building deformable object models, cite:
@inproceedings{yang2022banmo,
title={BANMo: Building Animatable 3D Neural Models from Many Casual Videos},
author={Yang, Gengshan and Vo, Minh and Neverova, Natalia and Ramanan, Deva and Vedaldi, Andrea and Joo, Hanbyul},
booktitle = {CVPR},
year={2022}
}
For building category body and pose models, cite:
@inproceedings{yang2023rac,
title={Reconstructing Animatable Categories from Videos},
author={Yang, Gengshan and Wang, Chaoyang and Reddy, N. Dinesh and Ramanan, Deva},
booktitle = {CVPR},
year={2023}
}
For object-scene reconstruction and extreme view synthesis, cite:
@article{song2023totalrecon,
title={Total-Recon: Deformable Scene Reconstruction for Embodied View Synthesis},
author={Song, Chonghyuk and Yang, Gengshan and Deng, Kangle and Zhu, Jun-Yan and Ramanan, Deva},
journal={arXiv},
year={2023}
}
For training feed-forward video/image shape and pose estimators, cite:
@inproceedings{tan2023distilling,
title={Distilling Neural Fields for Real-Time Articulated Shape Reconstruction},
author={Tan, Jeff and Yang, Gengshan and Ramanan, Deva},
booktitle={CVPR},
year={2023}
}
For the human-48 dataset cite:
Owner
- Name: lab4d-org
- Login: lab4d-org
- Kind: organization
- Repositories: 1
- Profile: https://github.com/lab4d-org
Citation (CITATION.cff)
cff-version: 1.2.0
title: Lab4d - A framework for in-the-wild 4D reconstruction from monocular videos
message: 'If you use this software, please cite it as below.'
type: software
authors:
- family-names: Yang
given-names: Gengshan
- family-names: Tan
given-names: Jeff
- family-names: Lyons
given-names: Alex
- family-names: Peri
given-names: Neehar
- family-names: Ramanan
given-names: Deva
url: 'https://github.com/lab4d-org/lab4d'
license: MIT
version: 0.0.0
date-released: '2023-06-30'
GitHub Events
Total
- Issues event: 3
- Watch event: 57
- Member event: 1
- Issue comment event: 1
- Push event: 3
- Pull request review event: 2
- Pull request event: 2
- Fork event: 4
Last Year
- Issues event: 3
- Watch event: 57
- Member event: 1
- Issue comment event: 1
- Push event: 3
- Pull request review event: 2
- Pull request event: 2
- Fork event: 4
Issues and Pull Requests
Last synced: 10 months ago
All Time
- Total issues: 0
- Total pull requests: 1
- Average time to close issues: N/A
- Average time to close pull requests: N/A
- Total issue authors: 0
- Total pull request authors: 1
- Average comments per issue: 0
- Average comments per pull request: 0.0
- Merged pull requests: 0
- Bot issues: 0
- Bot pull requests: 0
Past Year
- Issues: 0
- Pull requests: 1
- Average time to close issues: N/A
- Average time to close pull requests: N/A
- Issue authors: 0
- Pull request authors: 1
- Average comments per issue: 0
- Average comments per pull request: 0.0
- Merged pull requests: 0
- Bot issues: 0
- Bot pull requests: 0
Top Authors
Issue Authors
- zz7379 (3)
- Batwho (3)
- NielsRogge (1)
- figure317 (1)
- randomx207 (1)
- litchisea (1)
- ngoductuanlhp (1)
- LyndzP (1)
- limaolin2017 (1)
Pull Request Authors
- MightyChaos (1)
- limaolin2017 (1)
- ChaoyueSong (1)
Top Labels
Issue Labels
Pull Request Labels
Dependencies
- actions/checkout v3 composite
- actions/configure-pages v3 composite
- actions/deploy-pages v2 composite
- actions/upload-pages-artifact v1 composite
- conda-incubator/setup-miniconda v2 composite
- gradio ==3.28.3
- openmim *
- pyrender *
- pysdf *
- timm ==0.6.7