SNAP3D: Physically Grounded 3D Parts for Assembly from a Single Image

2026-09-11

AI Summary

本文提出了一种物理引导框架SNAP3D，通过解决部件间穿透问题、恢复接触图和引入参数化连接器，改进单图像部件感知3D生成的物理兼容性和稳定性。

Abstract

Part-aware 3D asset generation enables applications such as editing, articulation, simulation, and fabrication, yet existing methods can generate visually complete individual parts without ensuring that they form a valid physical assembly. Consequently, generated neighboring parts may interpenetrate, lack valid connections, or collapse under gravity. We propose a physics-guided framework for improving single-image part-aware 3D generation with physically compatible geometry and stable connections. Our method resolves inter-part penetration, recovers a contact graph between neighboring parts, and introduces parameterized connectors at their contact surfaces. Using feedback from physical simulation, we refine connector placement, orientation, and dimensions to improve assembly stability while preserving the generated geometry. We further introduce a physics-based evaluation protocol that complements conventional geometric metrics by directly testing assembly validity and stability under gravity. Experiments comparing against multiple part-aware 3D generators show substantial improvements in physical realizability and stability while maintaining geometric quality. We additionally validate the resulting parts through 3D printing and real-world assembly.

Problem

• 3D generation
• physical assembly
• inter-part penetration
• stable connections
• gravity

Innovation

• physics-guided framework
• physically compatible geometry
• stable connections
• parameterized connectors
• physical simulation feedback