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 autonomous driving, monocular sequences contain lots of information.Monocular depth estimation, camera ego-motion estimation and optical flowestimation in consecutive frames are high-profile concerns recently. Byanalyzing tasks above, pixels in the middle frame are modeled into three parts:the rigid region, the non-rigid region, and the occluded region. In jointunsupervised training of depth and pose, we can segment the occluded regionexplicitly. The occlusion information is used in unsupervised learning ofdepth, pose and optical flow, as the image reconstructed by depth-pose andoptical flow will be invalid in occluded regions. A less-than-mean mask isdesigned to further exclude the mismatched pixels interfered with by motion orillumination change in the training of depth and pose networks. This method isalso used to exclude some trivial mismatched pixels in the training of theoptical flow network. Maximum normalization is proposed for depth smoothnessterm to restrain depth degradation in textureless regions. In the occludedregion, as depth and camera motion can provide more reliable motion estimation,they can be used to instruct unsupervised learning of optical flow. Ourexperiments in KITTI dataset demonstrate that the model based on three regions,full and explicit segmentation of the occlusion region, the rigid region, andthe non-rigid region with corresponding unsupervised losses can improveperformance on three tasks significantly. The source code is available at:https://github.com/guangmingw/DOPlearning.

Unsupervised Learning of Depth, Optical Flow and Pose With Occlusion From 3D Geometry