Recently, records on stereo matching benchmarks are constantly broken by end-to-end disparity networks. However, the domain adaptation ability of these deep models is quite poor. Addressing such problem, we present a novel domain-adaptive pipeline called AdaStereo that aims to align multi-level representations for deep stereo matching networks. Compared to previous methods for adaptive stereo matching, our AdaStereo realizes a more standard, complete and effective domain adaptation pipeline. Firstly, we propose a non-adversarial progressive color transfer algorithm for input image-level alignment. Secondly, we design an efficient parameter-free cost normalization layer for internal feature-level alignment. Lastly, a highly related auxiliary task, self-supervised occlusion-aware reconstruction is presented to narrow down the gaps in output space. Our AdaStereo models achieve state-of-the-art cross-domain performance on multiple stereo benchmarks, including KITTI, Middlebury, ETH3D, and DrivingStereo, even outperforming disparity networks finetuned with target-domain ground-truths.
@article{arxiv.2004.04627,
title = {AdaStereo: A Simple and Efficient Approach for Adaptive Stereo Matching},
author = {Xiao Song and Guorun Yang and Xinge Zhu and Hui Zhou and Zhe Wang and Jianping Shi},
journal= {arXiv preprint arXiv:2004.04627},
year = {2021}
}