CorrMoE: Mixture of Experts with De-stylization Learning for Cross-Scene and Cross-Domain Correspondence Pruning

TL;DR

CorrMoE is a novel framework for correspondence pruning that improves robustness across different scenes and domains by using de-stylization and a mixture of experts with adaptive feature integration.

Contribution

It introduces a De-stylization Dual Branch and a Bi-Fusion Mixture of Experts module to handle cross-scene and cross-domain variations in correspondence pruning.

Findings

Achieves superior accuracy on benchmark datasets.

Demonstrates strong generalization across diverse scenes.

Outperforms state-of-the-art methods in robustness.

Abstract

Establishing reliable correspondences between image pairs is a fundamental task in computer vision, underpinning applications such as 3D reconstruction and visual localization. Although recent methods have made progress in pruning outliers from dense correspondence sets, they often hypothesize consistent visual domains and overlook the challenges posed by diverse scene structures. In this paper, we propose CorrMoE, a novel correspondence pruning framework that enhances robustness under cross-domain and cross-scene variations. To address domain shift, we introduce a De-stylization Dual Branch, performing style mixing on both implicit and explicit graph features to mitigate the adverse influence of domain-specific representations. For scene diversity, we design a Bi-Fusion Mixture of Experts module that adaptively integrates multi-perspective features through linear-complexity attention and dynamic expert routing. Extensive experiments on benchmark datasets demonstrate that CorrMoE achieves superior accuracy and generalization compared to state-of-the-art methods. The code and pre-trained models are available at https://github.com/peiwenxia/CorrMoE.