CorrAdaptor：面向对应关系剪枝的自适应局部上下文学习
CorrAdaptor: Adaptive Local Context Learning for Correspondence Pruning
AI总结：
针对现有对应关系剪枝方法依赖k近邻难以捕捉鲁棒上下文的问题，提出含显隐双分支局部图学习与运动注入模块的CorrAdaptor架构，在多类对应关系任务上取得SOTA性能。
摘要：
在计算机视觉与机器人领域，精确的像素级对应关系是实现运动恢复结构、同步定位与地图构建等高级任务的核心基础。现有对应关系剪枝方法通常依赖k近邻学习局部一致性，难以为每一组对应关系捕捉到鲁棒的上下文信息。本文提出CorrAdaptor这一全新架构，采用双分支结构，通过显式与隐式局部图学习自适应调整局部上下文。具体而言，显式分支使用基于KNN的图完成初始邻域识别，隐式分支则通过可学习矩阵对邻域进行软分配，自适应扩展局部上下文范围，显著提升了模型对复杂图像变化的鲁棒性与适配能力。此外，本文设计了运动注入模块，将运动一致性融入网络以抑制外点的影响，优化局部上下文学习，带来了性能的大幅提升。在大量基于对应关系的任务上的实验结果表明，CorrAdaptor在定性与定量层面均达到了当前最优性能。代码与预训练模型可访问https://github.com/TaoWangzj/CorrAdaptor获取。
英文摘要：
In the fields of computer vision and robotics, accurate pixel-level correspondences are essential for enabling advanced tasks such as structure-from-motion and simultaneous localization and mapping. Recent correspondence pruning methods usually focus on learning local consistency through k-nearest neighbors, which makes it difficult to capture robust context for each correspondence. We propose CorrAdaptor, a novel architecture that introduces a dual-branch structure capable of adaptively adjusting local contexts through both explicit and implicit local graph learning. Specifically, the explicit branch uses KNN-based graphs tailored for initial neighborhood identification, while the implicit branch leverages a learnable matrix to softly assign neighbors and adaptively expand the local context scope, significantly enhancing the model's robustness and adaptability to complex image variations. Moreover, we design a motion injection module to integrate motion consistency into the network to suppress the impact of outliers and refine local context learning, resulting in substantial performance improvements. The experimental results on extensive correspondence-based tasks indicate that our CorrAdaptor achieves state-of-the-art performance both qualitatively and quantitatively. The code and pre-trained models are available at https://github.com/TaoWangzj/CorrAdaptor.
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。
