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

This paper deals with a challenging, frequently encountered, yet not properlyinvestigated problem in two-frame optical flow estimation. That is, the inputframes are compounds of two imaging layers -- one desired background layer ofthe scene, and one distracting, possibly moving layer due to transparency orreflection. In this situation, the conventional brightness constancy constraint-- the cornerstone of most existing optical flow methods -- will no longer bevalid. In this paper, we propose a robust solution to this problem. Theproposed method performs both optical flow estimation, and image layerseparation. It exploits a generalized double-layer brightness consistencyconstraint connecting these two tasks, and utilizes the priors for both ofthem. Experiments on both synthetic data and real images have confirmed theefficacy of the proposed method. To the best of our knowledge, this is thefirst attempt towards handling generic optical flow fields of two-frame imagescontaining transparency or reflection.

Robust Optical Flow Estimation of Double-Layer Images under Transparency or Reflection