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

Dense image matching is a fundamental low-level problem in Computer Vision,which has received tremendous attention from both discrete and continuousoptimization communities. The goal of this paper is to combine the advantagesof discrete and continuous optimization in a coherent framework. We devise amodel based on energy minimization, to be optimized by both discrete andcontinuous algorithms in a consistent way. In the discrete setting, we proposea novel optimization algorithm that can be massively parallelized. In thecontinuous setting we tackle the problem of non-convex regularizers by aformulation based on differences of convex functions. The resulting hybriddiscrete-continuous algorithm can be efficiently accelerated by modern GPUs andwe demonstrate its real-time performance for the applications of dense stereomatching and optical flow.

Solving Dense Image Matching in Real-Time using Discrete-Continuous Optimization