发表机构
College of Future Information Technology, Fudan University; College of Intelligent Robotics and Advanced Manufacturing, Fudan University; University of Turku; Jihua Laboratory（复旦大学未来信息技术学院; 复旦大学智能机器人与先进制造学院; 图尔库大学; 季华实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出PG-Pose框架，结合平面高斯溅射重建与几何驱动优化，在无CAD模型条件下实现无纹理物体6D姿态估计，在OnePose-LowTexture数据集上达到94.2%精度，并成功应用于工业机器人抓取。
AI 中文摘要
在没有先验CAD模型的情况下估计无纹理物体的6D姿态，由于缺乏外观特征，仍然是一个关键挑战。虽然最近的通用方法减轻了对特定物体模型的依赖，但它们在低纹理物体上的性能往往受到底层表示中几何约束不足的限制。在这项工作中，我们提出了PG-Pose，一个结合了基于平面的高斯溅射（PGS）重建和几何驱动的姿态优化的几何感知框架。在离线表示提取阶段，从已知姿态的多视角参考RGB图像中提取物体的三种不同表示。PG-Pose重建3D高斯表示，并渲染高保真深度图，通过反投影生成3D点云。在在线姿态推理阶段，通过输入图像与重建的3D点云之间的2D-3D对应匹配来估计输入图像的初始姿态，然后使用PGS-Refiner进行迭代姿态优化。在OnePose-LowTexture数据集上的评估中，PG-Pose达到了94.2%的ADD(S)@0.1d平均精度，与最先进的（SOTA）基于GS的方法相比，平均精度提高了2.1%。为了进一步证明PG-Pose在工业机器人抓取任务中的有效性，我们将其部署在双臂工业机器人上，并成功实现了对未见物体的抓取任务。
英文摘要
Estimating the 6D pose of textureless objects without prior CAD models remains a critical challenge due to the lack of appearance features. While recent generalizable approaches alleviate the dependence on object-specific models, their performance on low-texture objects is often limited by insufficient geometric constraints in the underlying representations. In this work, we propose PG-Pose, a geometry-aware framework combining Planar-based Gaussian Splatting (PGS) reconstruction and Geometry-driven pose optimization. In the offline representation extraction stage, three distinct representations of the object are extracted from multi-view reference RGB images with known poses. PG-Pose reconstructs a 3D Gaussian representation and renders high-fidelity depth maps to generate 3D point clouds through back projection. In the online pose inference stage, the initial pose of the input image is estimated by 2D-3D correspondence matching between the input image and the reconstructed 3D point clouds, followed by a PGS-Refiner for iterative pose optimization. Evaluations on the OnePose-LowTexture datasets, PG-Pose achieves an average accuracy of 94.2% ADD(S)@0.1d, with a 2.1% improvement average accuracy compared with the state-of-the-art (SOTA) GS-based approach. To further demonstrate the effectiveness of PG-Pose for industrial robots in grasping tasks, we deploy it on a dual-arm industrial robot and successfully realize the grasping task on an unseen object.
Comments7 pages, 5 figures. Accepted by the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2026)
