CorrMoE：面向跨场景与跨域对应关系剪枝的去风格化学习混合专家模型
CorrMoE: Mixture of Experts with De-stylization Learning for Cross-Scene and Cross-Domain Correspondence Pruning
AI总结：
本文提出CorrMoE框架，通过去风格化双分支和双融合混合专家模块解决跨域与跨场景下的对应关系剪枝问题，显著提升了准确性和泛化能力。
摘要：
在图像对之间建立可靠的对应关系是计算机视觉中的一项基础任务，支撑着3D重建和视觉定位等应用。尽管近期的方法在从密集对应集中剪枝离群点方面取得了进展，但它们通常假设视觉域一致，并忽略了多样化场景结构带来的挑战。在本文中，我们提出了CorrMoE，一种新颖的对应关系剪枝框架，增强了在跨域和跨场景变化下的鲁棒性。为解决域偏移，我们引入了去风格化双分支，对隐式和显式图特征执行风格混合，以减轻特定域表示的不利影响。针对场景多样性，我们设计了双融合混合专家模块，通过线性复杂度注意力和动态专家路由自适应地整合多视角特征。在基准数据集上的大量实验表明，与最先进的方法相比，CorrMoE实现了更高的准确性和泛化能力。代码和预训练模型可在https://github.com/peiwenxia/CorrMoE获取。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
