解决跨场景跨域图像匹配中的误匹配问题，提升鲁棒性。
CorrMoE: Mixture of Experts with De-stylization Learning for Cross-Scene and Cross-Domain Correspondence Pruning
- 用双分支去风格化处理域偏移，融合隐式与显式特征。
- 设计双向融合专家模块，线性复杂度下自适应集成多视角特征。
- 在多个基准数据集上优于现有方法，适合实际部署的匹配任务。
建立图像对之间的可靠对应关系是计算机视觉的基础任务，支撑三维重建和视觉定位等应用。尽管近期方法在修剪密集对应集合中的离群点方面取得进展，但通常假设视觉域一致，忽视了不同场景结构带来的挑战。本文提出CorrMoE，一种增强跨域和跨场景变化下鲁棒性的对应关系剪枝框架。为应对域偏移，引入去风格化双分支结构，在隐式和显式图特征上进行风格混合，以减轻特定域表示的负面影响。针对场景多样性，设计双向融合专家模块，通过线性复杂度注意力和动态专家路由自适应整合多视角特征。在多个基准数据集上的大量实验表明，CorrMoE在准确性和泛化能力上均优于现有最先进方法。代码与预训练模型已公开于https://github.com/peiwenxia/CorrMoE。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。