PrimitiveAnything：基于自回归Transformer的人类手工3D基元组装生成

PrimitiveAnything: Human-Crafted 3D Primitive Assembly Generation with Auto-Regressive Transformer

May 7, 2025

作者: Jingwen Ye, Yuze He, Yanning Zhou, Yiqin Zhu, Kaiwen Xiao, Yong-Jin Liu, Wei Yang, Xiao Han

cs.AI

摘要

形状基元抽象，即将复杂的三维形状分解为简单几何元素的过程，在人类视觉认知中扮演着关键角色，并在计算机视觉与图形学领域有着广泛应用。尽管近期三维内容生成技术取得了显著进展，现有的基元抽象方法要么依赖于几何优化而缺乏深层次的语义理解，要么仅从特定类别的小规模数据集中学习，难以泛化至多样化的形状类别。我们提出了PrimitiveAnything，一个将形状基元抽象重新定义为基元组装生成任务的新颖框架。该框架包含一个基于形状条件的基元变换器用于自回归生成，以及一个无歧义的参数化方案，以统一方式表示多种类型的基元。通过直接从大规模人工制作的抽象中学习基元组装过程，PrimitiveAnything能够捕捉人类如何将复杂形状分解为基元元素。大量实验表明，PrimitiveAnything能够生成与人类感知高度一致且保持几何保真度的高质量基元组装，适用于多种三维应用，并展现出在游戏中支持基于基元的用户生成内容（UGC）的潜力。项目页面：https://primitiveanything.github.io

English

Shape primitive abstraction, which decomposes complex 3D shapes into simple geometric elements, plays a crucial role in human visual cognition and has broad applications in computer vision and graphics. While recent advances in 3D content generation have shown remarkable progress, existing primitive abstraction methods either rely on geometric optimization with limited semantic understanding or learn from small-scale, category-specific datasets, struggling to generalize across diverse shape categories. We present PrimitiveAnything, a novel framework that reformulates shape primitive abstraction as a primitive assembly generation task. PrimitiveAnything includes a shape-conditioned primitive transformer for auto-regressive generation and an ambiguity-free parameterization scheme to represent multiple types of primitives in a unified manner. The proposed framework directly learns the process of primitive assembly from large-scale human-crafted abstractions, enabling it to capture how humans decompose complex shapes into primitive elements. Through extensive experiments, we demonstrate that PrimitiveAnything can generate high-quality primitive assemblies that better align with human perception while maintaining geometric fidelity across diverse shape categories. It benefits various 3D applications and shows potential for enabling primitive-based user-generated content (UGC) in games. Project page: https://primitiveanything.github.io