SNAP3D: Physically Grounded 3D Parts for Assembly from a Single Image
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 27 of its 47 references that are in the map. First posted on arXiv 11 Sep 2026.
Builds on
27 of 47 references.
References · 27
- 2018PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understandingcited by 526
- 2025Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generationcited by 356
- 2016Learning Shape Abstractions by Assembling Volumetric Primitivescited by 181
- 2019Superquadrics Revisited: Learning 3D Shape Parsing beyond Cuboidscited by 124
- 2024SAMPart3D: Segment Any Part in 3D Objectscited by 97
- 2025PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformerscited by 84
- 2024SINGAPO: Single Image Controlled Generation of Articulated Parts in Objectscited by 69
- 2024PartGen: Part-level 3D Generation and Reconstruction with Multi-View Diffusion Modelscited by 62
- 2025OmniPart: Part-Aware 3D Generation with Semantic Decoupling and Structural Cohesioncited by 61
- 2025HoloPart: Generative 3D Part Amodal Segmentationcited by 60
- 2023IndustReal: Transferring Contact-Rich Assembly Tasks from Simulation to Realitycited by 53
- 2023CAGE: Controllable Articulation GEnerationcited by 52
15 more
- 2025Efficient Part-level 3D Object Generation via Dual Volume Packingcited by 48
- 2024PhyRecon: Physically Plausible Neural Scene Reconstructioncited by 45
- 2025X-Part: high fidelity and structure coherent shape decompositioncited by 44
- 2025P3-SAM: Native 3D Part Segmentationcited by 43
- 2024MeshArt: Generating Articulated Meshes with Structure-Guided Transformerscited by 41
- 2024Physically Compatible 3D Object Modeling from a Single Imagecited by 39
- 2024PhysPart: Physically Plausible Part Completion for Interactable Objectscited by 25
- 2025DSO: Aligning 3D Generators with Simulation Feedback for Physical Soundnesscited by 25
- 2024ArtFormer: Controllable Generation of Diverse 3D Articulated Objectscited by 22
- 2024Atlas3D: Physically Constrained Self-Supporting Text-to-3D for Simulation and Fabricationcited by 20
- 2023ASAP: Automated Sequence Planning for Complex Robotic Assembly with Physical Feasibilitycited by 18
- 2025GaussianArt: Unified Modeling of Geometry and Motion for Articulated Objectscited by 17
- 2025HoloScene: Simulation-Ready Interactive 3D Worlds from a Single Videocited by 14
- 2025Stable Part Diffusion 4D: Multi-View RGB and Kinematic Parts Video Generationcited by 5
- 2026CubePart: An Open-Vocabulary Part-Controllable 3D Generatorcited by 5
Built on by
Not cited yet.