Kavli Affiliate: Zheng Zhu
| First 5 Authors: Xianda Guo, Juntao Lu, Chenming Zhang, Yiqi Wang, Yiqun Duan
| Summary:
Stereo matching aims to estimate the disparity between matching pixels in a
stereo image pair, which is of great importance to robotics, autonomous
driving, and other computer vision tasks. Despite the development of numerous
impressive methods in recent years, replicating their results and determining
the most suitable architecture for practical application remains challenging.
Addressing this gap, our paper introduces a comprehensive benchmark focusing on
practical applicability rather than solely on performance enhancement.
Specifically, we develop a flexible and efficient stereo matching codebase,
called OpenStereo. OpenStereo includes training and inference codes of more
than 10 network models, making it, to our knowledge, the most complete stereo
matching toolbox available. Based on OpenStereo, we conducted experiments and
have achieved or surpassed the performance metrics reported in the original
paper. Additionally, we carry out an exhaustive analysis and deconstruction of
recent developments in stereo matching through comprehensive ablative
experiments. These investigations inspired the creation of StereoBase, a strong
baseline model. Our StereoBase ranks 1st on SceneFlow, KITTI 2015, 2012
(Reflective) among published methods and achieves the best performance across
all metrics. In addition, StereoBase has strong cross-dataset
generalization.Code is available at
url{https://github.com/XiandaGuo/OpenStereo}.
| Search Query: ArXiv Query: search_query=au:”Zheng Zhu”&id_list=&start=0&max_results=3