English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Stereo matching, a pivotal technique in computer vision, plays a crucial rolein robotics, autonomous navigation, and augmented reality. Despite thedevelopment of numerous impressive methods in recent years, replicating theirresults and determining the most suitable architecture for practicalapplication remains challenging. Addressing this gap, our paper introduces acomprehensive benchmark focusing on practical applicability rather than solelyon performance enhancement. Specifically, we develop a flexible and efficientstereo matching codebase, called OpenStereo. OpenStereo includes training andinference codes of more than 12 network models, making it, to our knowledge,the most complete stereo matching toolbox available. Based on OpenStereo, weconducted experiments on the SceneFlow dataset and have achieved or surpassedthe performance metrics reported in the original paper. Additionally, weconduct an in-depth revisitation of recent developments in stereo matchingthrough ablative experiments. These investigations inspired the creation ofStereoBase, a simple yet strong baseline model. Our extensive comparativeanalyses of StereoBase against numerous contemporary stereo matching methods onthe SceneFlow dataset demonstrate its remarkably strong performance. The sourcecode is available at https://github.com/XiandaGuo/OpenStereo.

OpenStereo: A Comprehensive Benchmark for Stereo Matching and Strong Baseline