StereoFlowGAN: Co-training for Stereo and Flow with Unsupervised Domain Adaptation
Zhexiao Xiong (Washington University in St. Louis),* Feng Qiao (RWTH Aachen University), Yu Zhang (Bastian Solutions), Nathan Jacobs (Washington University in St. Louis)
The 34th British Machine Vision Conference
Abstract
We introduce a novel training strategy for stereo matching and optical flow estimation that utilizes image-to-image translation between synthetic and real image domains. Our approach enables the training of models that excel in real image scenarios while relying solely on ground-truth information from synthetic images. To facilitate task-agnostic domain adaptation and the training of task-specific components, we introduce a bidirectional feature warping module that handles both left-right and forward-backward directions. Experimental results show competitive performance over previous domain translation-based methods, which substantiate the efficacy of our proposed framework, effectively leveraging the benefits of unsupervised domain adaptation, stereo matching, and optical flow estimation.Video
Citation
@inproceedings{Xiong_2023_BMVC,
author = {Zhexiao Xiong and Feng Qiao and Yu Zhang and Nathan Jacobs},
title = {StereoFlowGAN: Co-training for Stereo and Flow with Unsupervised Domain Adaptation},
booktitle = {34th British Machine Vision Conference 2023, {BMVC} 2023, Aberdeen, UK, November 20-24, 2023},
publisher = {BMVA},
year = {2023},
url = {https://papers.bmvc2023.org/0240.pdf}
}
Copyright © 2023
The British Machine Vision Conference is organised by