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.
翻译:立体相匹配是各种应用的基本基础,但大多数立体相匹配方法的通用性能较差,需要固定的差别搜索范围。此外,目前的立体相匹配方法侧重于仅具有正差的场景,但忽视了包含正差和负差的场景,如三维电影。在本文件中,我们提出了一个新的立体相匹配管道,首先根据双视视视镜差异计算半重差异图,然后根据单眼提示完成其余部分。新的立体相匹配管道具有以下优势:1)比大多数现有立体相匹配方法的通用性效果更好;2)放宽固定差异搜索范围的局限性;3)可以处理涉及正差和负差的场景,后者有更大的潜在应用,例如3D多媒体和VR/AR的视图合成。实验结果表明我们新的立体相匹配管道的有效性。