AdaStereo: A Simple and Efficient Approach for Adaptive Stereo Matching
This addresses the domain adaptation problem for stereo matching in computer vision, which is incremental as it builds on existing methods to improve cross-domain performance.
The paper tackles the poor domain adaptation ability of deep stereo matching networks by introducing AdaStereo, a pipeline that aligns multi-level representations, achieving state-of-the-art cross-domain performance on benchmarks like KITTI and Middlebury, even outperforming models finetuned with target-domain ground-truths.
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.