资源分类
》 资源 》论文》A Convex Formulation of Continuous Multi-label Problems

A Convex Formulation of Continuous Multi-label Problems

2020-03-30 | |  70 |   44 |   0

Abstract

We propose a spatially continuous formulation of Ishikawa’s discrete multi-label problem. We show that the resulting non-convex vari- ational problem can be reformulated as a convex variational problem via embedding in a higher dimensional space. This variational problem can be interpreted as a minimal surface problem in an anisotropic Rie- mannian space. In several stereo experiments we show that the proposed continuous formulation is superior to its discrete counterpart in terms of computing time, memory efficiency and metrication errors.

上一篇：Sparse Structures in L-Infinity Norm Minimization for Structure and Motion Reconstruction*

下一篇：Robust 3D Pose Estimation and Ef ficient 2D Region-Based Segmentation from a 3D Shape Prior

用户评价
全部评价

热门资源

  • Learning to Predi...

    Much of model-based reinforcement learning invo...

  • Stratified Strate...

    In this paper we introduce Stratified Strategy ...

  • The Variational S...

    Unlike traditional images which do not offer in...

  • A Mathematical Mo...

    Direct democracy, where each voter casts one vo...

  • Rating-Boosted La...

    The performance of a recommendation system reli...