PicoPose：面向新物体位姿估计的渐进式像素到像素对应学习
PicoPose: Progressive Pixel-to-Pixel Correspondence Learning for Novel Object Pose Estimation
AI总结：
本文提出PicoPose框架，通过模板匹配、全局二维仿射回归和局部对应偏移细化的三阶段像素对应学习，提升PnP/RANSAC位姿估计，并在BOP七个核心数据集上达到SOTA。
摘要：
基于RGB的新物体位姿估计对于机器人应用中的快速部署至关重要，但零样本泛化仍是一项关键挑战。本文提出PicoPose，这是一个旨在利用三阶段像素到像素对应学习过程来解决该任务的新颖框架。首先，PicoPose将RGB观测中的特征与渲染物体模板中的特征进行匹配，识别最佳匹配模板并建立粗略对应。其次，PicoPose通过从粗略对应图中全局回归一个二维仿射变换来平滑这些对应，该变换包括平面内旋转、尺度和二维平移。第三，PicoPose将仿射变换应用于最佳匹配模板的特征图，并学习局部区域内的对应偏移，以获得细粒度对应。通过逐步细化对应，PicoPose显著提高了经由PnP/RANSAC计算的物体位姿精度。PicoPose在BOP基准的七个核心数据集上取得了最先进性能，展现出对新物体的出色泛化能力。代码和训练模型可在https://github.com/foollh/PicoPose获取。
英文摘要：
RGB-based novel object pose estimation is critical for rapid deployment in robotic applications, yet zero-shot generalization remains a key challenge. In this paper, we introduce PicoPose, a novel framework designed to tackle this task using a three-stage pixel-to-pixel correspondence learning process. Firstly, PicoPose matches features from the RGB observation with those from rendered object templates, identifying the best-matched template and establishing coarse correspondences. Secondly, PicoPose smooths the correspondences by globally regressing a 2D affine transformation, including in-plane rotation, scale, and 2D translation, from the coarse correspondence map. Thirdly, PicoPose applies the affine transformation to the feature map of the best-matched template and learns correspondence offsets within local regions to achieve fine-grained correspondences. By progressively refining the correspondences, PicoPose significantly improves the accuracy of object poses computed via PnP/RANSAC. PicoPose achieves state-of-the-art performance on the seven core datasets of the BOP benchmark, demonstrating exceptional generalization to novel objects. Code and trained models are available at https://github.com/foollh/PicoPose.
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。
