Home

Awesome

Iterative Residual Refinement <br/> for Joint Optical Flow and Occlusion Estimation

<img src=output.gif>

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 orginally developed under Anaconda(Python 3.6), PyTorch 0.4.1 and CUDA 8.0 on Ubuntu 16.04.

  1. Please install the followings:

    • Anaconda
    • PyTorch (now compatible with PyTorch 1.5.0)
    • tqdm (conda install -c conda-forge tqdm==4.40.0)
    • (any missing packages that the code requires)

  2. 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