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

In this paper, we propose CGI-Stereo, a novel neural network architecturethat can concurrently achieve real-time performance, competitive accuracy, andstrong generalization ability. The core of our CGI-Stereo is a Context andGeometry Fusion (CGF) block which adaptively fuses context and geometryinformation for more effective cost aggregation and meanwhile provides feedbackto feature learning to guide more effective contextual feature extraction. Theproposed CGF can be easily embedded into many existing stereo matchingnetworks, such as PSMNet, GwcNet and ACVNet. The resulting networks show asignificant improvement in accuracy. Specially, the model which incorporatesour CGF with ACVNet ranks $1^{st}$ on the KITTI 2012 and 2015 leaderboardsamong all the published methods. We further propose an informative and concisecost volume, named Attention Feature Volume (AFV), which exploits a correlationvolume as attention weights to filter a feature volume. Based on CGF and AFV,the proposed CGI-Stereo outperforms all other published real-time methods onKITTI benchmarks and shows better generalization ability than other real-timemethods. Code is available at https://github.com/gangweiX/CGI-Stereo.

CGI-Stereo: Accurate and Real-Time Stereo Matching via Context and Geometry Interaction