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

Optical flow estimation is an essential task in self-driving systems, whichhelps autonomous vehicles perceive temporal continuity information ofsurrounding scenes. The calculation of all-pair correlation plays an importantrole in many existing state-of-the-art optical flow estimation methods.However, the reliance on local knowledge often limits the model's accuracyunder complex street scenes. In this paper, we propose a new deep networkarchitecture for optical flow estimation in autonomous driving--CSFlow, whichconsists of two novel modules: Cross Strip Correlation module (CSC) andCorrelation Regression Initialization module (CRI). CSC utilizes a stripingoperation across the target image and the attended image to encode globalcontext into correlation volumes, while maintaining high efficiency. CRI isused to maximally exploit the global context for optical flow initialization.Our method has achieved state-of-the-art accuracy on the public autonomousdriving dataset KITTI-2015. Code is publicly available athttps://github.com/MasterHow/CSFlow.

CSFlow: Learning Optical Flow via Cross Strip Correlation for Autonomous Driving