Skip to content
Iterative Residual Refinement for Joint Optical Flow and Occlusion Estimation (CVPR 2019)
Branch: master
Clone or download
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
datasets init Jun 14, 2019
flyingchairsocc dataset Jul 22, 2019
models supporting pytorch 1.1, cuda 9.0 Jul 17, 2019
optim init Jun 14, 2019
saved_check_point/pwcnet init Jun 14, 2019
scripts init Jun 14, 2019
utils init Jun 14, 2019
LICENSE Initial commit Jun 13, 2019
README.md Update README.md Jul 17, 2019
__init__.py init Jun 14, 2019
augmentations.py init Jun 14, 2019
commandline.py init Jun 14, 2019
configuration.py init Jun 14, 2019
install.sh init Jun 14, 2019
logger.py init Jun 14, 2019
losses.py init Jun 14, 2019
main.py init Jun 14, 2019
runtime.py init Jun 14, 2019
tools.py init Jun 14, 2019

README.md

Iterative Residual Refinement
for Joint Optical Flow and Occlusion Estimation

This repository is the PyTorch implementation of the paper:

Iterative Residual Refinement for Joint Optical Flow and Occlusion Estimation (CVPR 2019)
Junhwa Hur and Stefan Roth
Department of Computer Science, TU Darmstadt
[Preprint][Proceeding][Supplemental]

Please cite the paper below if you find our paper and source codes are useful.

@inproceedings{Hur:2019:IRR,  
  Author = {Junhwa Hur and Stefan Roth},  
  Booktitle = {CVPR},  
  Title = {Iterative Residual Refinement for Joint Optical Flow and Occlusion Estimation},  
  Year = {2019}  
}

Contact: junhwa.hur[at]visinf.tu-darmstadt.de

Getting started

This code has been developed under Anaconda(Python 3.6), Pytorch 0.4.1 and CUDA 8.0 on Ubuntu 16.04.

  1. Please install the followings:

    • Anaconda (Python 3.6)
    • PyTorch 0.4.1 (Linux, Conda, Python 3.6, CUDA 8.0)
      • For PyTorch 1.1, Python 3.7, CUDA >= 9.0, the correlation module needs to be installed accordingly:
        • Please move all files in models/correlation_package_cu9 to models/correlation_package (overwritting)
        • Depending on your system, configure -gencode, -ccbin, cuda-path in models/correlation_package/setup.py accordingly
    • tqdm (conda install -c conda-forge tqdm)
  2. Then, install the correlation package:

    ./install.sh
    
  3. The datasets used for this projects are followings:

Training

The scripts folder contains training scripts of experiments demonstrated in the paper.
To train the model, you can simply run the script file, e.g., ./IRR-PWC_flyingChairsOcc.sh.
In script files, please configure your own experiment directory (EXPERIMENTS_HOME) and dataset directory in your local system (e.g., SINTEL_HOME or KITTI_HOME).

Pretrained Models

The saved_check_point contains the pretrained models of i) baseline, ii) baseline + irr, and iii) full models.
Additional pretrained models in the ablations study (Table 1 in the main paper) and their training scripts are available upon request.

Inference

The scripts for testing the pre-trained models are located in scripts/validation.

Acknowledgement

Portions of the source code (e.g., training pipeline, runtime, argument parser, and logger) are from Jochen Gast

You can’t perform that action at this time.