Skip to content
No description, website, or topics provided.
Jupyter Notebook Python
Branch: master
Clone or download
Hiroharu Kato
Hiroharu Kato initial commit
Latest commit 92a2deb Oct 24, 2019
Type Name Latest commit message Commit time
Failed to load latest commit information.
DRS initial commit Oct 24, 2019
Dataset initial commit Oct 24, 2019
IoU_evaluation initial commit Oct 24, 2019
voxels initial commit Oct 24, 2019
LICENSE initial commit Oct 24, 2019 initial commit Oct 24, 2019
teaser.png initial commit Oct 24, 2019

Differentiable Ray Sampling for Neural 3D Representation

This software is developed as a part of Preferred Networks 2019 Research Internships.
The main developer is N. H. Shimada.

The code realizes a differentiable renderer for neural 3D representation. The prediction model can be trained via only 2D images and conducts 3D reconstruction from a single RGB image (as below).
For more details, please refer to slides and blog (Japanese).

Teaser Image

Pre-trained models

Please check out the jupyter notebook 1 which shows the qualititive results using the trained models in the case of car class.

Training and Evaluating

There must be -

  • Creating the dataset of 10 rendered images of each car from ShapeNet V1 using blender.
    (Please refer to the paper and codes of Tulsiani+ CVPR 2017)

Run the main code

python3 DRS/ 0
to train networks and save them into DRS/save/.

Evaluating models


MIT License (see the LICENSE file for details).

You can’t perform that action at this time.