search

niladridutt / Diffusion-3D-Features

Diffusion 3D Features (Diff3F): Decorating Untextured Shapes with Distilled Semantic Features [CVPR 2024]
https://diff3f.github.io/
MIT License
59 stars 12 forks source link

readme

Diffusion 3D Features (Diff3F): Decorating Untextured Shapes with Distilled Semantic Features [CVPR 2024]

ArXiv PWC PyTorch

Project Webpage | Paper

Setup

conda env create -f environment.yaml
conda activate diff3f

Additional prerequisites

Install pytorch3d

conda install -c fvcore -c iopath -c conda-forge fvcore iopath

You might face difficulty in installing pytorch3d or encounter the error ModuleNotFoundError: No module named 'pytorch3d during run time. Unfortunately, this is because pytorch3d could not be installed properly. Please refer here for alternate ways to install pytorch3d.

Usage

Please check the example notebook test_correspondence.ipynb for details on computing features for a mesh and finding correspondence/part segmentations.

Additional details

This project will follow a staged code release.

The meshes provided in the meshes directory are provided as examples from various sources and we do not claim any copyright.

BibTeX

If you find our research useful, please consider citing it as follows.

@article{dutt2023diffusion,
    title={Diffusion 3D Features (Diff3F): Decorating Untextured Shapes with Distilled Semantic Features}, 
    author={Dutt, Niladri Shekhar and Muralikrishnan, Sanjeev and Mitra, Niloy J.},
    journal={arXiv preprint arXiv:2311.17024},
    year={2023},
}