BANG: Dividing 3D Assets via Generative Exploded Dynamics
Open Access
- 27 July 2025
- journal article
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 44 (4) , 1-21
Abstract
3D creation has always been a unique human strength, driven by our ability to deconstruct and reassemble objects using our eyes, mind and hand. However, current 3D design tools struggle to replicate this natural process, requiring considerable artistic expertise and manual labor. This paper introduces BANG, a novel generative approach that bridges 3D generation and reasoning, allowing for intuitive and flexible part-level decomposition of 3D objects. At the heart of BANG is "Generative Exploded Dynamics", which creates a smooth sequence of exploded states for an input geometry, progressively separating parts while preserving their geometric and semantic coherence. BANG utilizes a pre-trained large-scale latent diffusion model, fine-tuned for exploded dynamics with a lightweight exploded view adapter, allowing precise control over the decomposition process. It also incorporates a temporal attention module to ensure smooth transitions and consistency across time. BANG enhances control with spatial prompts, such as bounding boxes and surface regions, enabling users to specify which parts to decompose and how. This interaction can be extended with multimodal models like GPT-4, enabling 2D-to-3D manipulations for more intuitive and creative workflows. The capabilities of BANG extend to generating detailed part-level geometry, associating parts with functional descriptions, and facilitating component-aware 3D creation and manufacturing workflows. Additionally, BANG offers applications in 3D printing, where separable parts are generated for easy printing and reassembly. In essence, BANG enables seamless transformation from imaginative concepts to detailed 3D assets, offering a new perspective on creation that resonates with human intuition.Keywords
All Related Versions
Funding Information
- National Key R&D Program of China (2022YFF0902301)
- NSFC programs (61976138)
- NSFC programs (61977047)
- STCSM (2015F0203-000-06)
- SHMEC (2019-01-07-00-01-E00003)
This publication has 67 references indexed in Scilit:
- DreamDissector: Learning Disentangled Text-to-3D Generation from 2D Diffusion Priors2024
- TransCAD: A Hierarchical Transformer for CAD Sequence Inference from Point Clouds2024
- ComboVerse: Compositional 3D Assets Creation Using Spatially-Aware Diffusion Guidance2024
- MVDiffusion++: A Dense High-Resolution Multi-view Diffusion Model for Single or Sparse-View 3D Object Reconstruction2024
- MeshSegmenter: Zero-Shot Mesh Semantic Segmentation via Texture Synthesis2024
- PointLLM: Empowering Large Language Models to Understand Point Clouds2024
- STAG4D: Spatial-Temporal Anchored Generative 4D Gaussians2024
- ShapeLLM: Universal 3D Object Understanding for Embodied Interaction2024
- Compositional 3D Scene Generation using Locally Conditioned Diffusion2024
- PartNet: A Large-Scale Benchmark for Fine-Grained and Hierarchical Part-Level 3D Object Understanding2019