[论文] SemEllipsoid: Semantic-aware Shape Abstraction with Ellipsoid

论文概要

研究领域: CV 作者: Kuankuan Cheng, Haocheng Yuan, Changjian Li 发布时间: 2026-10-30 arXiv: 2610.42145

中文摘要

使用一组基元表示三维形状（即形状抽象）是计算机图形学中一个活跃的研究课题，由于基元表示的紧凑性和计算效率，在形状理解、分析和模拟中有广泛应用。先前的工作主要集中在几何感知的形状抽象上，其目标是在保持几何保真度的同时用最少的基元逼近输入形状。然而，这些方法往往忽视了语义一致性，不可避免地导致跨越多个语义部分的基元。这种不一致可能在零件级形状编辑或操作等下游任务中造成不良的伪影。本文引入一个新任务——语义感知的形状抽象，目标是生成既几何忠实又语义一致的抽象结果，确保每个基元严格遵循单一语义部分而不跨越语义边界。我们提出SemEllipsoid，一种使用椭球基元解决该问题的新方法。其核心思想是利用大规模基础模型提供的语义线索，将语义约束注入基元优化过程。我们设计了一个完全可微的投影-混合-评估方案，用于度量与输入语义掩码的语义偏差，并构建了一种交替优化策略，迭代求解最优语义分配和基元配置。我们的方法不基于学习，无需数据收集或网络训练，能够很好地推广到任意类别的形状，还支持根据用户需求提供不同层次的抽象。大量实验和评估在多个3D形状数据集上验证了我们方法的有效性。

原文摘要

Representing 3D shapes using a set of primitives - known as shape abstraction - is an actively studied problem in computer graphics with wide applications in shape understanding, analysis, and simulation due to the compactness and computational efficiency of the primitive-based representation. Prior work has primarily focused on geometry-aware shape abstraction, where the objective is to approximate the input shape with a minimal set of primitives while preserving geometric fidelity. However, these methods often overlook semantic consistency, inevitably leading to primitives that span across multiple semantic parts. Such inconsistency can cause undesirable artifacts in downstream tasks such as part-level shape editing or manipulation. In this paper, we introduce a new task - semantic-aware...

#论文 #arXiv #CV #小凯