真实场景下的铰接物体估计
Articulated Object Estimation in the Wild
AI总结：
针对现有铰接物体估计方法在真实无约束环境中失效的问题，提出结合深度点跟踪与因子图优化的ArtiPoint框架，可从动态RGB-D视频中鲁棒估计铰接特性，同时构建首个自我中心真实场景铰接数据集Arti4D，验证了方法的优越性能。
摘要：
理解铰接物体的3D运动对机器人场景理解、移动操作和运动规划至关重要。现有的铰接性估计方法主要聚焦于受控环境，假设相机视角固定或能直接观测到物体的各种状态，这类方法在更真实的无约束环境中往往会失效。相比之下，人类能通过观察他人操作物体轻松推断出铰接特性。受此启发，我们提出了ArtiPoint这一新型估计框架，能够在动态相机运动和部分可观测的条件下推断铰接物体模型。该框架将深度点跟踪与因子图优化框架相结合，可直接从原始RGB-D视频中鲁棒地估计铰接部件的运动轨迹和铰接轴。为推动该领域的后续研究，我们构建了Arti4D，这是首个以自我为中心的真实场景数据集，可在场景层面捕捉铰接物体的交互过程，并附带铰接标签和真实相机位姿。我们将ArtiPoint与多种经典方法和基于学习的基线方法进行了基准测试，证明其在Arti4D上的性能更优。我们已在https://artipoint.cs.uni-freiburg.de公开代码和Arti4D数据集。
英文摘要：
Understanding the 3D motion of articulated objects is essential in robotic scene understanding, mobile manipulation, and motion planning. Prior methods for articulation estimation have primarily focused on controlled settings, assuming either fixed camera viewpoints or direct observations of various object states, which tend to fail in more realistic unconstrained environments. In contrast, humans effortlessly infer articulation by watching others manipulate objects. Inspired by this, we introduce ArtiPoint, a novel estimation framework that can infer articulated object models under dynamic camera motion and partial observability. By combining deep point tracking with a factor graph optimization framework, ArtiPoint robustly estimates articulated part trajectories and articulation axes directly from raw RGB-D videos. To foster future research in this domain, we introduce Arti4D, the first ego-centric in-the-wild dataset that captures articulated object interactions at a scene level, accompanied by articulation labels and ground-truth camera poses. We benchmark ArtiPoint against a range of classical and learning-based baselines, demonstrating its superior performance on Arti4D. We make code and Arti4D publicly available at https://artipoint.cs.uni-freiburg.de.
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。
