COG：面向无监督单参考新物体姿态估计的置信度感知最优几何对应
COG: Confidence-aware Optimal Geometric Correspondence for Unsupervised Single-reference Novel Object Pose Estimation
把跨视角对应从不可微的一对一硬匹配换成带逐点置信度的最优传输软匹配，并用视觉基础模型的语义先验做正则，这套「置信度作为 OT 边缘分布」的做法可直接迁移到任何需要鲁棒特征匹配的位姿/配准任务。
原文依据 formulates correspondence estimation as a confidence-aware optimal transport problem
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论仅凭单张参考视图估计新物体的 6DoF 姿态，由于遮挡、视角变化与离群点而颇具挑战。其核心难点在于寻找鲁棒的跨视角对应，因为现有方法往往依赖离散的一对一匹配，这种匹配不可微且容易坍缩到稀疏关键点上。我们提出置信度感知最优几何对应（COG），一个将对应估计建模为置信度感知最优传输问题的无监督框架。COG 通过预测逐点置信度并将其作为最优传输的边缘分布注入，抑制非重叠区域，从而产生均衡的软对应。来自视觉基础模型的语义先验进一步对对应关系进行正则化，带来稳定的姿态估计。该设计将置信度融入对应寻找与姿态估计流程，使无监督学习成为可能。实验表明，无监督的 COG 达到与监督方法相当的性能，而监督版 COG 则优于这些方法。代码：https://github.com/YC-Che/COG
英文原文摘要 1108 字符
Estimating the 6DoF pose of a novel object with a single reference view is challenging due to occlusions, view-point changes, and outliers. A core difficulty lies in finding robust cross-view correspondences, as existing methods often rely on discrete one-to-one matching that is non-differentiable and tends to collapse onto sparse keypoints. We propose Confidence-aware Optimal Geometric Correspondence (COG), an unsupervised framework that formulates correspondence estimation as a confidence-aware optimal transport problem. COG produces balanced soft correspondences by predicting point-wise confidences and injecting them as optimal transport marginals, suppressing non-overlapping regions. Semantic priors from vision foundation models further regularize the correspondences, leading to stable pose estimation. This design integrates confidence into the correspondence finding and pose estimation pipeline, enabling unsupervised learning. Experiments show unsupervised COG achieves comparable performance to supervised methods, and supervised COG outperforms them. Codes: https://github.com/YC-Che/COG