Learning Intra-view and Cross-view Geometric Knowledge for Stereo Matching

TL;DR

This paper introduces ICGNet, a novel neural network that effectively integrates intra-view and cross-view geometric knowledge, including occlusion and matching constraints, to significantly enhance stereo matching accuracy.

Contribution

The paper presents a new network architecture that combines intra-view and cross-view geometric insights using interest points, addressing limitations of prior methods.

Findings

ICGNet outperforms existing models in stereo matching accuracy.

Incorporating cross-view geometric relationships improves disparity estimation.

Extensive experiments validate the effectiveness of the proposed approach.

Abstract

Geometric knowledge has been shown to be beneficial for the stereo matching task. However, prior attempts to integrate geometric insights into stereo matching algorithms have largely focused on geometric knowledge from single images while crucial cross-view factors such as occlusion and matching uniqueness have been overlooked. To address this gap, we propose a novel Intra-view and Cross-view Geometric knowledge learning Network (ICGNet), specifically crafted to assimilate both intra-view and cross-view geometric knowledge. ICGNet harnesses the power of interest points to serve as a channel for intra-view geometric understanding. Simultaneously, it employs the correspondences among these points to capture cross-view geometric relationships. This dual incorporation empowers the proposed ICGNet to leverage both intra-view and cross-view geometric knowledge in its learning process, substantially improving its ability to estimate disparities. Our extensive experiments demonstrate the superiority of the ICGNet over contemporary leading models.