[论文] Point2Part: Unified 3D Partitioning from Point Prompts

论文概要

研究领域: CV 作者: Hao-Tang Tsui, Yu-Rou Tuan, Xiaoxuan Ma, Nicolas Ugrinovic, Takaaki Shiratori, Kris Kitani 发布时间: 2026-09-29 arXiv: 2609.38180

中文摘要

现有的3D部件分解方法并不一定能将原始形状分割为不重叠的部件并完整覆盖整个形状，产生的重叠或间隙会阻碍下游部件级应用。本文将部件分解重新定义为对整个形状的联合分割，使预测的部件互不重叠且共同恢复完整形状。我们的核心洞见是：部件分解应联合考虑所有目标部件，而非独立建模每个部件。为此，我们开发了一个可从图像或网格进行可控3D部件分解的提示驱动模型。用户可以通过3D点提示指定所需部件，实现可控分解。给定每个目标部件的一个点提示，模型将输出对应部件作为整个形状的完整分割。我们基于预训练的3D生成模型构建，首先从输入图像或网格获取形状隐编码，然后引入提示编码器将每个3D点提示映射为部件token，同时关注形状隐编码。为了解码所需部件，我们提出了一种新颖的部件解码器，以从粗到细的方式将整体形状与所有部件token联合打分，将形状体积内的每个位置精确分配给唯一部件。我们在共享的形状隐空间中执行部件分解，从而实现了图像到部件生成、网格到部件生成和部件分割的统一模型。我们的方法在三个任务的所有部件质量指标上均优于现有工作，并将部件间的兼容性提升了数量级。代码和模型将开源。

原文摘要

Existing 3D part decomposition methods do not necessarily partition the original shape into non-overlapping parts that collectively cover the entire shape, allowing overlaps or gaps that hinder downstream part-level applications. We instead formulate part decomposition as a joint partitioning of the entire shape, where the predicted parts are non-overlapping and jointly recover the entire shape. Our key insight is that part decomposition should consider all desired parts jointly, rather than modeling each part independently. To this end, we develop a promptable model for 3D part decomposition from images or meshes. Users can specify desired parts through 3D point prompts for controllable decomposition. Given one point prompt per desired part, our model produces the corresponding parts as a...

#论文 #arXiv #CV #小凯