Zoom and Learn: Generalizing Deep Stereo Matching to Novel Domains

Jiahao Pang, Wenxiu Sun, Chengxi Yang, Jimmy Ren, Ruichao Xiao, Jin Zeng, Liang Lin; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018, pp. 2070-2079

Abstract


Despite the recent success of stereo matching with convolutional neural networks (CNNs), it remains arduous to generalize a pre-trained deep stereo model to a novel domain. A major difficulty is to collect accurate ground-truth disparities for stereo pairs in the target domain. In this work, we propose a self-adaptation approach for CNN training, utilizing both synthetic training data (with ground-truth disparities) and stereo pairs in the new domain (without ground-truths). Our method is driven by two empirical observations. By feeding real stereo pairs of different domains to stereo models pre-trained with synthetic data, we see that: i) a pre-trained model does not generalize well to the new domain, producing artifacts at boundaries and ill-posed regions; however, ii) feeding an up-sampled stereo pair leads to a disparity map with extra details. To avoid i) while exploiting ii), we formulate an iterative optimization problem with graph Laplacian regularization. At each iteration, the CNN adapts itself better to the new domain: we let the CNN learn its own higher-resolution output; at the meanwhile, a graph Laplacian regularization is imposed to discriminatively keep the desired edges while smoothing out the artifacts. We demonstrate the effectiveness of our method in two domains: daily scenes collected by smartphone cameras, and street views captured in a driving car.

Related Material


[pdf] [Supp] [arXiv]
[bibtex]
@InProceedings{Pang_2018_CVPR,
author = {Pang, Jiahao and Sun, Wenxiu and Yang, Chengxi and Ren, Jimmy and Xiao, Ruichao and Zeng, Jin and Lin, Liang},
title = {Zoom and Learn: Generalizing Deep Stereo Matching to Novel Domains},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2018}
}