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 recent years, deep neural networks have shown remarkable progress in densedisparity estimation from dynamic scenes in monocular structured light systems.However, their performance significantly drops when applied in unseenenvironments. To address this issue, self-supervised online adaptation has beenproposed as a solution to bridge this performance gap. Unlike traditionalfine-tuning processes, online adaptation performs test-time optimization toadapt networks to new domains. Therefore, achieving fast convergence during theadaptation process is critical for attaining satisfactory accuracy. In thispaper, we propose an unsupervised loss function based on long sequentialinputs. It ensures better gradient directions and faster convergence. Our lossfunction is designed using a multi-frame pattern flow, which comprises a set ofsparse trajectories of the projected pattern along the sequence. We estimatethe sparse pseudo ground truth with a confidence mask using a filter-basedmethod, which guides the online adaptation process. Our proposed frameworksignificantly improves the online adaptation speed and achieves superiorperformance on unseen data.

Online Adaptive Disparity Estimation for Dynamic Scenes in Structured Light Systems