https://github.com/shubhtuls/drc
Code release for "Multi-view Supervision for Single-view Reconstruction via Differentiable Ray Consistency" (CVPR 2017)
https://github.com/shubhtuls/drc
3d-reconstruction deep-learning weakly-supervised
Last synced: about 1 year ago
JSON representation
Code release for "Multi-view Supervision for Single-view Reconstruction via Differentiable Ray Consistency" (CVPR 2017)
- Host: GitHub
- URL: https://github.com/shubhtuls/drc
- Owner: shubhtuls
- Created: 2017-04-13T00:00:57.000Z (about 9 years ago)
- Default Branch: master
- Last Pushed: 2019-01-04T16:18:53.000Z (over 7 years ago)
- Last Synced: 2024-08-04T04:08:58.837Z (almost 2 years ago)
- Topics: 3d-reconstruction, deep-learning, weakly-supervised
- Language: Lua
- Homepage: https://shubhtuls.github.io/drc/
- Size: 2.86 MB
- Stars: 162
- Watchers: 14
- Forks: 32
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
- awesome-3D-vision - Multi-view Supervision for Single-view Reconstruction via Differentiable Ray Consistency
README
# Multi-view Supervision for Single-view Reconstruction via Differentiable Ray Consistency
Shubham Tulsiani, Tinghui Zhou, Alexei A. Efros, Jitendra Malik. In CVPR, 2017.
[Project Page](https://shubhtuls.github.io/drc/)
## Demo and Pre-trained Models
Please check out the [interactive notebook](demo/demo.ipynb) which shows reconstructions using the learned models. You'll need to -
- Install a working implementation of torch and itorch.
- Download the pre-trained models for [Pascal3D (490MB)](https://people.eecs.berkeley.edu/~shubhtuls/cachedir/drc/snapshots/pascalModels.tar.gz) and [ShapeNet (250MB)](https://people.eecs.berkeley.edu/~shubhtuls/cachedir/drc/snapshots/shapenetModels.tar.gz). Extract the pretrained models to 'cachedir/snapshots/{pascal,shapenet}/'
- Edit the path to the blender executable in the demo script.
## Loss Function Compilation
To use our proposed loss function for training, we need to compile the C implementation so it can be used in Torch.
```
cd drcLoss
luarocks make rpsem-alpha-1.rockspec
```
## Training and Evaluating
For training your own models and evaluating those, or for reproducing the main experiments in the paper, please see the detailed README files for [PASCAL3D](docs/pascal.md) or [ShapeNet](docs/snet.md).
## Additional Dependencies
You'll need to install some additional dependencies (json and matio).
```
sudo apt-get install libmatio2
luarocks install matio
luarocks install json
```
### Citation
If you use this code for your research, please consider citing:
```
@inProceedings{drcTulsiani17,
title={Multi-view Supervision for Single-view Reconstruction
via Differentiable Ray Consistency},
author = {Shubham Tulsiani
and Tinghui Zhou
and Alexei A. Efros
and Jitendra Malik},
booktitle={Computer Vision and Pattern Regognition (CVPR)},
year={2017}
}
```