Skip to content
Adversarial Texture Optimization from RGB-D Scans (CVPR 2020).
Python C++ Cuda Shell CMake
Branch: master
Clone or download

Latest commit

Latest commit 306344e Mar 25, 2020

Files

Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
data change download path Mar 20, 2020
res add readme Mar 16, 2020
src preprocessing readme Mar 16, 2020
.gitignore
LICENSE Initial commit Mar 14, 2020
README.md Update README.md Mar 24, 2020

README.md

AdversarialTexture

Adversarial Texture Optimization from RGB-D Scans (CVPR 2020).

AdversarialTexture Teaser

Scanning Data Download

Please refer to data directory for details.

Before run following scripts, please modify the data_path in src/config.py as the absolute path of the data folder (e.g. Adversarial/data) where you download all data.

Prepare for Training (Optimization)

Please refer to src/preprocessing directory for details.

Run Training (Optimization)

Consider execute run_all.sh in parallel.

cd src/textureoptim
python gen_script.py
sh run_all.sh

Result Visualization

The result will be stored in data/result/chairID/chairID.png. You can use them to replace the corresponding default texture in data/shape, and use meshlab to open obj files to see the results.

Alternatively, we provide a simple script to render results. You will be able to see the rendering comparison in data/visual.

cd src
python visualize.py

Authors

© Jingwei Huang, Stanford University

IMPORTANT: If you use this code please cite the following in any resulting publication:

@article{huang2020adversarial,
  title={Adversarial Texture Optimization from RGB-D Scans},
  author={Huang, Jingwei and Thies, Justus and Dai, Angela and Kundu, Abhijit and Jiang, Chiyu Max and Guibas, Leonidas and Nie{\ss}ner, Matthias and Funkhouser, Thomas},
  journal={arXiv preprint arXiv:2003.08400},
  year={2020}
}

The rendering process is a modification of pyRender.

You can’t perform that action at this time.