SemStereo: Semantic-Constrained Stereo Matching Network for Remote Sensing

TL;DR

This paper introduces SemStereo, a novel network that explicitly and implicitly integrates semantic segmentation with stereo matching for remote sensing, improving accuracy in both tasks.

Contribution

It proposes a new cascade structure and modules that enforce semantic constraints on stereo matching, capturing their inherent connections more effectively.

Findings

Achieves state-of-the-art results on US3D and WHU datasets.

Enhances stereo matching accuracy with semantic guidance.

Improves semantic segmentation performance through stereo constraints.

Abstract

Semantic segmentation and 3D reconstruction are two fundamental tasks in remote sensing, typically treated as separate or loosely coupled tasks. Despite attempts to integrate them into a unified network, the constraints between the two heterogeneous tasks are not explicitly modeled, since the pioneering studies either utilize a loosely coupled parallel structure or engage in only implicit interactions, failing to capture the inherent connections. In this work, we explore the connections between the two tasks and propose a new network that imposes semantic constraints on the stereo matching task, both implicitly and explicitly. Implicitly, we transform the traditional parallel structure to a new cascade structure termed Semantic-Guided Cascade structure, where the deep features enriched with semantic information are utilized for the computation of initial disparity maps, enhancing semantic guidance. Explicitly, we propose a Semantic Selective Refinement (SSR) module and a Left-Right Semantic Consistency (LRSC) module. The SSR refines the initial disparity map under the guidance of the semantic map. The LRSC ensures semantic consistency between two views via reducing the semantic divergence after transforming the semantic map from one view to the other using the disparity map. Experiments on the US3D and WHU datasets demonstrate that our method achieves state-of-the-art performance for both semantic segmentation and stereo matching.