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/

Zendy Plus

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

Zendy Tools

Zendy Open

Convex relaxations of nonconvex multilabel problems have been demonstrated toproduce superior (provably optimal or near-optimal) solutions to a variety ofclassical computer vision problems. Yet, they are of limited practical use asthey require a fine discretization of the label space, entailing a huge demandin memory and runtime. In this work, we propose the first sublabel accurateconvex relaxation for vectorial multilabel problems. The key idea is that weapproximate the dataterm of the vectorial labeling problem in a piecewiseconvex (rather than piecewise linear) manner. As a result we have a morefaithful approximation of the original cost function that provides a meaningfulinterpretation for the fractional solutions of the relaxed convex problem. Innumerous experiments on large-displacement optical flow estimation and on colorimage denoising we demonstrate that the computed solutions have superiorquality while requiring much lower memory and runtime.

Sublabel-Accurate Convex Relaxation of Vectorial Multilabel Energies