A new stereo formulation not using pixel and disparity models

03/05/2018
by   Kiyoshi Oguri, et al.
0

We introduce a new stereo formulation which does not use pixel and disparity models. Many problems in vision are treated as assigning each pixel a label. Disparities are labels for stereo. Such pixel-labeling problems are naturally represented in terms of energy minimization, where the energy function has two terms: one term penalizes solutions that inconsistent with the observed data, the other term enforces spatial smoothness. Graph cuts are one of the effi- cient methods for solving energy minimization. However, exact minimization of multi labeling problems can be performed by graph cuts only for the case with convex smoothness terms. In pixel-disparity formulation, convex smoothness terms do not generate well reconstructed 3D results. Thus, truncated linear or quadratic smoothness terms, etc. are used, where approximate energy minimization is necessary. In this paper, we introduce a new site-labeling formulation, where the sites are not pixels but lines in 3D space, labels are not disparities but depth numbers. For this formulation, visibility reasoning is naturally included in the energy function. In addition, this formulation allows us to use a small smoothness term, which does not affect the 3D results much. This makes the optimization step very simple, so we could develop an approximation method for graph cut itself (not for energy minimization) and a high performance GPU graph cut program. For Tsukuba stereo pair in Middlebury data set, we got the result in 5ms using GTX1080GPU, 19ms using GTX660GPU.

READ FULL TEXT

page 6

page 7

research
10/29/2014

Extended Dynamic Programming and Fast Multidimensional Search Algorithm for Energy Minization in Stereo and Motion

This paper presents a novel extended dynamic programming approach for en...
research
06/13/2023

Continuous Cost Aggregation for Dual-Pixel Disparity Extraction

Recent works have shown that depth information can be obtained from Dual...
research
08/26/2017

Stereo Matching With Color-Weighted Correlation, Hierarchical Belief Propagation And Occlusion Handling

In this paper, we contrive a stereo matching algorithm with careful hand...
research
01/15/2016

Stereo Matching by Joint Energy Minimization

In [18], Mozerov et al. propose to perform stereo matching as a two-step...
research
11/24/2014

Iteratively Reweighted Graph Cut for Multi-label MRFs with Non-convex Priors

While widely acknowledged as highly effective in computer vision, multi-...
research
04/23/2020

Fast Convex Relaxations using Graph Discretizations

Matching and partitioning problems are fundamentals of computer vision a...
research
04/11/2016

Semantic 3D Reconstruction with Continuous Regularization and Ray Potentials Using a Visibility Consistency Constraint

We propose an approach for dense semantic 3D reconstruction which uses a...

Please sign up or login with your details

Forgot password? Click here to reset