Fully automatic texturing of 3D shapes with rich SV-BRDF reflectance models.
Code and Data
All of the code relevant to this project is available on github.
Material (SVBRDF) Dataset
- Scanned Materials (859 MB)
- V-Ray Materials (782 MB)
- Adobe Stock and Poliigon materials have restrictive licenses. Directions for getting these materials can be found here.
Material Classifier
- Synthetic Training Data (1.5 GB, LMDB)
- Trained Weights (155 MB)
Photorealistic Shape Dataset
Provided as Blender scenes. Note that these archives contain the raw output of our pipeline which means they also contain failure cases. More detailed JSON inference results may be found in the Github repository.
Important Note: Blender >=2.79 is required to render these scenes due to the use of the Principled BRDF.
- Herman Miller Chairs (636 shapes, 6.0 GB)
- ShapeNet Chairs (15,576 shapes, 146 GB)
Bibtex
@article{photoshape2018,
author = {Park, Keunhong and Rematas, Konstantinos and Farhadi, Ali and Seitz, Steven M.},
title = {PhotoShape: Photorealistic Materials for Large-Scale Shape Collections},
journal = {ACM Trans. Graph.},
issue_date = {November 2018},
volume = {37},
number = {6},
month = nov,
year = {2018},
articleno = {192},
}
Acknowledgements
This work was supported by the Samsung Scholarship, the Allen Institute for Artificial Intelligence, Intel, Google, and the National Science Foundation (IIS1538618).