A novel stereo matching pipeline with robustness and unfixed disparity search range

TL;DR

This paper introduces a new stereo matching pipeline that improves generalization, relaxes fixed disparity range constraints, and handles scenes with both positive and negative disparities, enhancing applications like 3D view synthesis.

Contribution

A novel stereo matching pipeline that combines semi-dense disparity maps with monocular cues, enabling better generalization and handling of negative disparities.

Findings

Outperforms existing methods in generalization

Removes fixed disparity search range limitation

Successfully handles scenes with negative disparities

Abstract

Stereo matching is an essential basis for various applications, but most stereo matching methods have poor generalization performance and require a fixed disparity search range. Moreover, current stereo matching methods focus on the scenes that only have positive disparities, but ignore the scenes that contain both positive and negative disparities, such as 3D movies. In this paper, we present a new stereo matching pipeline that first computes semi-dense disparity maps based on binocular disparity, and then completes the rest depending on monocular cues. The new stereo matching pipeline have the following advantages: It 1) has better generalization performance than most of the current stereo matching methods; 2) relaxes the limitation of a fixed disparity search range; 3) can handle the scenes that involve both positive and negative disparities, which has more potential applications, such as view synthesis in 3D multimedia and VR/AR. Experimental results demonstrate the effectiveness of our new stereo matching pipeline.