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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Learning depth and optical flow via deep neural networks by watching videoshas made significant progress recently. In this paper, we jointly solve the twotasks by exploiting the underlying geometric rules within stereo videos.Specifically, given two consecutive stereo image pairs from a video, we firstestimate depth, camera ego-motion and optical flow from three neural networks.Then the whole scene is decomposed into moving foreground and static backgroundby compar- ing the estimated optical flow and rigid flow derived from the depthand ego-motion. We propose a novel consistency loss to let the optical flowlearn from the more accurate rigid flow in static regions. We also design arigid alignment module which helps refine ego-motion estimation by using theestimated depth and optical flow. Experiments on the KITTI dataset show thatour results significantly outperform other state-of- the-art algorithms. Sourcecodes can be found at https: //github.com/baidu-research/UnDepthflow

Joint Unsupervised Learning of Optical Flow and Depth by Watching Stereo Videos