NARF24: 面向隐式渲染的关节式物体结构估计
NARF24: Estimating Articulated Object Structure for Implicit Rendering
AI总结：
针对机器人领域关节式物体表征需兼顾几何纹理与关节参数的难题，提出NARF24方法，结合少量场景学习的通用NeRF表征与部件分割估计物体结构，实现位姿条件渲染。
摘要：
关节式物体及其表征是机器人面临的一项难题。这类物体不仅需要几何与纹理表征，还需要表征构成每个关节的各类连接与关节参数。我们提出一种方法，可在少量采集的场景中学习通用的Neural Radiance Field（神经辐射场，NeRF）表征。该表征与基于部件的图像分割相结合，生成隐式空间部件定位，由此可估计关节式物体的连接性与关节参数，从而实现基于位姿配置的渲染。
英文摘要：
Articulated objects and their representations pose a difficult problem for robots. These objects require not only representations of geometry and texture, but also of the various connections and joint parameters that make up each articulation. We propose a method that learns a common Neural Radiance Field (NeRF) representation across a small number of collected scenes. This representation is combined with a parts-based image segmentation to produce an implicit space part localization, from which the connectivity and joint parameters of the articulated object can be estimated, thus enabling configuration-conditioned rendering.
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。
