PrimitiveAnything：基於自回歸Transformer的人類手工3D基元組裝生成

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

形狀基元抽象，即將複雜的三維形體分解為簡單幾何元素，在人類視覺認知中扮演著關鍵角色，並在計算機視覺與圖形學領域具有廣泛應用。儘管近年來三維內容生成技術取得了顯著進展，現有的基元抽象方法要么依賴於語義理解有限的幾何優化，要么從小規模、特定類別的數據集中學習，難以泛化至多樣化的形體類別。我們提出了PrimitiveAnything，這是一種新穎的框架，將形狀基元抽象重新表述為基元組裝生成任務。PrimitiveAnything包含一個基於形狀條件的基元Transformer用於自迴歸生成，以及一個無歧義的參數化方案，以統一方式表示多種類型的基元。該框架直接從大規模人工製作的抽象中學習基元組裝過程，使其能夠捕捉人類如何將複雜形體分解為基元元素。通過大量實驗，我們證明PrimitiveAnything能夠生成高質量的基元組裝，這些組裝不僅更好地符合人類感知，同時在多樣化的形體類別中保持幾何保真度。它為多種三維應用帶來益處，並展現了在遊戲中實現基於基元的用戶生成內容（UGC）的潛力。項目頁面：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