https://github.com/isarandi/nlf

[NeurIPS 2024] Neural Localizer Fields for Continuous 3D Human Pose and Shape Estimation
https://github.com/isarandi/nlf

3d-human-mesh 3d-human-pose-estimation 3d-human-shape-and-pose-estimation human-mesh-reconstruction human-mesh-recovery pytorch tensorflow

Last synced: about 14 hours ago
JSON representation

[NeurIPS 2024] Neural Localizer Fields for Continuous 3D Human Pose and Shape Estimation

• Host: GitHub
• URL: https://github.com/isarandi/nlf
• Owner: isarandi
• License: mit
• Created: 2024-08-25T14:14:33.000Z (5 months ago)
• Default Branch: main
• Last Pushed: 2024-12-12T18:16:26.000Z (about 1 month ago)
• Last Synced: 2025-01-07T14:07:02.834Z (8 days ago)
• Topics: 3d-human-mesh, 3d-human-pose-estimation, 3d-human-shape-and-pose-estimation, human-mesh-reconstruction, human-mesh-recovery, pytorch, tensorflow
• Language: Python
• Homepage: https://istvansarandi.com/nlf
• Size: 328 KB
• Stars: 214
• Watchers: 17
• Forks: 8
• Open Issues: 5
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# Neural Localizer Fields for Continuous 3D Human Pose and Shape Estimation

* [NeurIPS'24 paper](https://arxiv.org/abs/2407.07532) by István Sárándi and Gerard Pons-Moll

* [Project page](https://istvansarandi.com/nlf)

Models for PyTorch and TensorFlow are available for noncommercial research use under Releases, and usage examples are given in `demo.ipynb`. Stay tuned for more detailed docs.

Training code is provided for TensorFlow (PyTorch version underway).

## Acknowledgments

This work was supported by the German Federal Ministry of Education and Research (BMBF): Tübingen AI Center, FKZ: 01IS18039A. This work is funded by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) – 409792180 (Emmy Noether Programme, project: Real Virtual Humans). GPM is a member of the Machine Learning Cluster of Excellence, EXC number 2064/1 –Project number 390727645. The project was made possible by funding from the Carl Zeiss Foundation.

## BibTeX

```

@article{sarandi2024nlf,

    title     = {Neural Localizer Fields for Continuous 3D Human Pose and Shape Estimation},

    author    = {S\'ar\'andi, Istv\'an and Pons-Moll, Gerard},

    booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},

    year      = {2024}

}

```