发表机构
Southeast University; Purdue University（东南大学; 普渡大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
WAPR是一种零样本广角姿态精修模型，通过旋转对称先验和角度平衡损失，在快速推理下实现未见物体6D姿态估计的最先进性能。
AI 中文摘要
现实世界应用要求6D姿态估计在准确性、速度和可扩展性方面能够适应未见物体。本文介绍了WAPR，一种零样本广角姿态精修模型，能够精修旋转偏差高达90度的候选姿态。每个检测到的物体实例仅需12个候选姿态，WAPR支持每帧1秒内的快速推理，并达到每秒最多25个检测物体实例的姿态估计吞吐量。为了支持旋转对称物体的广角训练，WAPR利用旋转对称先验在损失计算前对对称等价姿态目标进行规范化。我们进一步构建了SA6D，一个包含此类先验的大规模6D训练数据集。SA6D为944个GSO扫描获取了KASAL辅助的旋转对称先验，并通过几何和纹理增强将其扩展为约50K个增强物体实例和约2M张渲染的RGB-D图像。此外，角度平衡损失通过减少无信息的大误差案例的影响，稳定了不同角度范围的学习。在七个BOP核心数据集上的实验表明，WAPR在快速和无约束推理设置下，在未见物体6D姿态定位和检测方面达到了最先进的性能。项目页面：此https URL。
英文摘要
Real-world applications require 6D pose estimation to be accurate, fast, and scalable to unseen objects. This paper introduces WAPR, a zero-shot wide-angle pose refinement model that refines candidate poses with rotational deviations up to 90 degrees. With as few as 12 candidate poses per detected object instance, WAPR supports fast inference within 1 s per frame and reaches a pose-estimation throughput of up to 25 detected object instances per second. To support wide-angle training for rotationally symmetric objects, WAPR uses rotational symmetry priors to canonicalize symmetry-equivalent pose targets before loss computation. We further construct SA6D, a large-scale 6D training dataset with such priors. SA6D obtains KASAL-assisted rotational symmetry priors for 944 GSO scans and expands them through geometry and texture augmentation into about 50K augmented object instances and about 2M rendered RGB-D images. In addition, an angle-balanced loss stabilizes learning across different angular ranges by reducing the influence of uninformative large-error cases. Experiments on seven BOP core datasets show that WAPR achieves state-of-the-art performance in unseen-object 6D pose localization and detection under both fast and unconstrained inference settings. Project page: https://github.com/WangYuLin-SEU/WAPR.
CommentsAccepted to ECCV 2026. 19 pages, 4 figures. Yulin Wang and Mengting Hu contributed equally. Corresponding author: Chen Luo
Journal refIn: Computer Vision - ECCV 2026, LNCS vol. 17016, pp. 221-239. Springer, Cham (2026)
DOI：10.1007/978-3-032-37383-0_13
