PoseGAM：基于几何感知多视图推理的鲁棒未见物体位姿估计
PoseGAM: Robust Unseen Object Pose Estimation via Geometry-Aware Multi-View Reasoning
把多视图基础模型当作位姿回归器，用点云几何与几何表征网络特征两路注入物体几何先验，绕开显式 2D-3D 对应匹配，可直接迁移到无模板、无 CAD 模型的未见物体位姿估计与抓取场景。
原文依据 directly predicts object pose from a query image and multiple template images, eliminating the need for explicit matching
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论6D 物体位姿估计旨在预测物体相对于相机的变换，对未见物体而言仍具挑战性。现有方法通常依赖在查询图像与物体模型或模板图像之间显式构建特征对应关系。本文提出 PoseGAM，一个几何感知的多视图框架，直接从查询图像与多张模板图像预测物体位姿，无需显式匹配。该方法建立在近期基于多视图的基础模型架构之上，通过两种互补机制引入物体几何信息：显式的基于点的几何，以及由几何表征网络学习到的特征。此外，我们构建了一个大规模合成数据集，包含超过 19 万个物体，覆盖多样化的环境条件，以增强鲁棒性与泛化能力。在多个基准上的大量评测表明，本方法达到最优性能，相较先前方法平均 AR 提升 5.1%，在个别数据集上提升最高达 17.6%，表明对未见物体具有强泛化能力。
英文原文摘要 1178 字符
6D object pose estimation, which predicts the transformation of an object relative to the camera, remains challenging for unseen objects. Existing approaches typically rely on explicitly constructing feature correspondences between the query image and either the object model or template images. In this work, we propose PoseGAM, a geometry-aware multi-view framework that directly predicts object pose from a query image and multiple template images, eliminating the need for explicit matching. Built upon recent multi-view-based foundation model architectures, the method integrates object geometry information through two complementary mechanisms: explicit point-based geometry and learned features from geometry representation networks. In addition, we construct a large-scale synthetic dataset containing more than 190k objects under diverse environmental conditions to enhance robustness and generalization. Extensive evaluations across multiple benchmarks demonstrate our state-of-the-art performance, yielding an average AR improvement of 5.1% over prior methods and achieving up to 17.6% gains on individual datasets, indicating strong generalization to unseen objects.