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 stereo-matching knowledge distillation methods of the self-supervisedmonocular depth estimation, the stereo-matching network's knowledge isdistilled into a monocular depth network through pseudo-depth maps. In thesemethods, the learning-based stereo-confidence network is generally utilized toidentify errors in the pseudo-depth maps to prevent transferring the errors.However, the learning-based stereo-confidence networks should be trained withground truth (GT), which is not feasible in a self-supervised setting. In thispaper, we propose a method to identify and filter errors in the pseudo-depthmap using multiple disparity maps by checking their consistency without theneed for GT and a training process. Experimental results show that the proposedmethod outperforms the previous methods and works well on variousconfigurations by filtering out erroneous areas where the stereo-matching isvulnerable, especially such as textureless regions, occlusion boundaries, andreflective surfaces.

Stereo-Matching Knowledge Distilled Monocular Depth Estimation Filtered by Multiple Disparity Consistency