CVNov 21, 2016

Sublabel-Accurate Discretization of Nonconvex Free-Discontinuity Problems

arXiv:1611.06987v214 citations
Originality Incremental advance
AI Analysis

This work addresses discretization challenges in computer vision and image processing, offering incremental improvements for tasks like segmentation and denoising.

The paper tackles the discretization of nonconvex free-discontinuity problems by deriving sublabel-accurate multilabeling approaches from convex relaxations, extending them to general regularizations and applying them to the vectorial Mumford-Shah functional, resulting in more precise solutions with fewer labels in experiments.

In this work we show how sublabel-accurate multilabeling approaches can be derived by approximating a classical label-continuous convex relaxation of nonconvex free-discontinuity problems. This insight allows to extend these sublabel-accurate approaches from total variation to general convex and nonconvex regularizations. Furthermore, it leads to a systematic approach to the discretization of continuous convex relaxations. We study the relationship to existing discretizations and to discrete-continuous MRFs. Finally, we apply the proposed approach to obtain a sublabel-accurate and convex solution to the vectorial Mumford-Shah functional and show in several experiments that it leads to more precise solutions using fewer labels.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes