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

Self-supervised deep learning-based 3D scene understanding methods canovercome the difficulty of acquiring the densely labeled ground-truth and havemade a lot of advances. However, occlusions and moving objects are still someof the major limitations. In this paper, we explore the learnable occlusionaware optical flow guided self-supervised depth and camera pose estimation byan adaptive cross weighted loss to address the above limitations. Firstly, weexplore to train the learnable occlusion mask fused optical flow network by anocclusion-aware photometric loss with the temporally supplemental informationand backward-forward consistency of adjacent views. And then, we design anadaptive cross-weighted loss between the depth-pose and optical flow loss ofthe geometric and photometric error to distinguish the moving objects whichviolate the static scene assumption. Our method shows promising results onKITTI, Make3D, and Cityscapes datasets under multiple tasks. We also show goodgeneralization ability under a variety of challenging scenarios.

Self-supervised Learning of Occlusion Aware Flow Guided 3D Geometry Perception with Adaptive Cross Weighted Loss from Monocular Videos