ConceptPose：基于概念向量的免训练零样本物体姿态估计
ConceptPose: Training-Free Zero-Shot Object Pose Estimation using Concept Vectors
用 VLM 的显著性图构造逐点概念向量的 3D 概念图，再靠 3D-3D 对应做无训练 6DoF 相对姿态估计，为无 CAD 模型、无数据集训练的物体姿态估计提供了一条可复用的表征与匹配思路。
原文依据 ConceptPose leverages a vision-language-model (VLM) to create open-vocabulary 3D concept maps
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论物体姿态估计是计算机视觉与机器人领域的基础任务，但现有方法大多需要大量针对特定数据集的训练。与此同时，大规模视觉语言模型展现出显著的零样本能力。本工作将这两个方向连接起来，提出 ConceptPose，一个既免训练又免模型的物体姿态估计框架。ConceptPose 利用视觉语言模型（VLM）构建开放词表的 3D 概念图，其中每个点都被赋予由显著性图得到的概念向量。通过在概念图之间建立稳健的 3D-3D 对应关系，本方法能够精确估计 6DoF 相对姿态。在无需任何针对物体或数据集的训练的情况下，本方法在常见的零样本相对姿态估计基准上取得了最优结果，平均 ADD(-S) 分数相对最强基线提升 62%，其中包括使用大量数据集特定训练的方法。
英文原文摘要 982 字符
Object pose estimation is a fundamental task in computer vision and robotics, yet most methods require extensive, dataset-specific training. Concurrently, large-scale vision language models show remarkable zero-shot capabilities. In this work, we bridge these two worlds by introducing ConceptPose, a framework for object pose estimation that is both training-free and model-free. ConceptPose leverages a vision-language-model (VLM) to create open-vocabulary 3D concept maps, where each point is tagged with a concept vector derived from saliency maps. By establishing robust 3D-3D correspondences across concept maps, our approach allows precise estimation of 6DoF relative pose. Without any object or dataset-specific training, our approach achieves state-of-the-art results on common zero shot relative pose estimation benchmarks, outperforming the strongest baseline by a relative 62% in average ADD(-S) score, including methods that utilize extensive dataset-specific training.