We propose a novel spatially continuous framework for convex relaxations based on functional lifting. Our method can be interpreted as a sublabel-accurate solution to multilabel problems. We show that previously proposed functional lifting methods optimize an energy which is linear between two labels and hence require (often infinitely) many labels for a faithful approximation. In contrast, the proposed formulation is based on a piecewise convex approximation and therefore needs far fewer labels -see Fig. 1. In comparison to recent MRF-based approaches, our method is formulated in a spatially continuous setting and shows less grid bias. Moreover, in a local sense, our formulation is the tightest possible convex relaxation. It is easy to implement and allows an efficient primal-dual optimization on GPUs. We show the effectiveness of our approach on several computer vision problems. * Those authors contributed equally. Pock et al. [17], 48 labels, 1.49 GB, 52s.Proposed, 8 labels, 0.49 GB, 30s.

Convex relaxations of multilabel problems have been demonstrated to produce provably optimal or near-optimal solutions to a variety of computer vision problems. Yet, they are of limited practical use as they require a fine discretization of the label space, entailing a huge demand in memory and runtime. In this work, we propose the first sublabel accurate convex relaxation for vectorial multilabel problems. Our key idea is to approximate the dataterm in a piecewise convex (rather than piecewise linear) manner. As a result we have a more faithful approximation of the original cost function that provides a meaningful interpretation for fractional solutions of the relaxed convex problem.

We systematically study the local single-valuedness of the Bregman proximal mapping and local smoothness of the Bregman-Moreau envelope under relative prox-regularity, an extension of prox-regularity for nonconvex functions which has been originally introduced by Poliquin and Rockafellar. Although, we focus on the left Bregman proximal mapping, a translation result yields analogue (and partially sharp) results for the right Bregman proximal mapping. The class of relatively prox-regular functions significantly extends the recently considered class of relatively hypoconvex functions. In particular, relative prox-regularity allows for functions with possibly nonconvex domain. Moreover, as a main source of examples, in analogy to the classical setting, we introduce relatively amenable functions by invoking the recently proposed notion of smooth adaptability or relative smoothness. Exemplarily we apply our theory to interpret joint alternating Bregman minimization with proximal regularization, locally, as a Bregman proximal gradient algorithm.Keywords: Bregman-Moreau envelope · Bregman proximal mapping · prox-regularity · amenable functions 2000 Mathematics Subject Classification: 49J52 · 65K05 · 65K10 · 90C26

This paper introduces a novel algorithm for transductive inference in higher-order MRFs, where the unary energies are parameterized by a variable classifier. The considered task is posed as a joint optimization problem in the continuous classifier parameters and the discrete label variables. In contrast to prior approaches such as convex relaxations, we propose an advantageous decoupling of the objective function into discrete and continuous subproblems and a novel, efficient optimization method related to ADMM. This approach preserves integrality of the discrete label variables and guarantees global convergence to a critical point. We demonstrate the advantages of our approach in several experiments including video object segmentation on the DAVIS data set and interactive image segmentation.

No abstract