Levy驱动的对应关系估计用于配准
Levy-Driven Correspondence Estimation for Registration
浏览论文内容
中文总结 AI 辅助
提出LevyMatch，利用Lévy过程随机跳跃细化软匹配矩阵，并采用前置加载Gamma策略优化更新时序，在4DMatch和4DLoMatch上提升非刚性配准的NFMR和IR。
中文摘要 AI 辅助
当点云重叠度低或经历非刚性变形时，寻找可靠的点对应关系是困难的。迭代细化可以纠正不确定的匹配，但昂贵的网络评估限制了更新的次数。我们提出了LevyMatch，一种使用随机跳跃来细化软匹配矩阵的Lévy驱动方法。在每一步中，网络利用当前匹配状态和几何信息来预测目标匹配矩阵。布朗参考桥给出了朝向该目标更新的显式公式。Gamma随机时钟为每次更新设置时间步长。更新后的匹配为下一次目标预测提供新的几何反馈。我们进一步提出了一种固定的前置加载Gamma策略，该策略将更多的期望时钟时间分配给早期更新，而将较少的时间分配给后期更新，无需重新训练或额外的网络评估。对相同采样的Gamma增量进行重新排序表明，将较大的增量放在早期比放在后期能获得更高的精度。在4DMatch和4DLoMatch上，我们的方法在非刚性特征匹配召回率（NFMR）和内点率（IR）上均优于对比方法。前置加载策略在4DMatch上实现了93.09%的NFMR和92.11%的IR，在4DLoMatch上实现了82.79%的NFMR和79.07%的IR。
英文摘要
Finding reliable point correspondences is difficult when point clouds have low overlap or undergo non-rigid deformation. Iterative refinement can correct uncertain matches, but costly network evaluations limit the number of updates. We present LevyMatch, a Lévy-driven method that uses random jumps to refine a soft matching matrix. At each step, a network uses the current matching state and geometric information to predict a target matching matrix. A Brownian reference bridge gives an explicit formula for the update toward this target. A Gamma random clock sets the time step for each update. The updated matches provide new geometric feedback for the next target prediction. We further propose a fixed front-loaded Gamma policy that assigns more expected clock time to early updates and less to later ones, without retraining or extra network evaluations. Reordering the same sampled Gamma increments shows that placing larger increments early gives higher accuracy than placing them late. On 4DMatch and 4DLoMatch, our method improves both non-rigid feature matching recall (NFMR) and inlier ratio (IR) over the compared methods. The front-loaded policy achieves 93.09% NFMR and 92.11% IR on 4DMatch, and 82.79% NFMR and 79.07% IR on 4DLoMatch.
