PartCrafter: Structured 3DMesh Generation via Compositional Latent Diffusion Transformers
–Neural Information Processing Systems
We introduce PARTCRAFTER, the first structured 3D generative model that jointly synthesizes multiple semantically meaningful and geometrically distinct 3D meshes from a single RGB image. Unlike existing methods that either produce monolithic 3D shapes or follow two-stage pipelines, i.e. first segmenting an image and then reconstructing each segment, PARTCRAFTER adopts a unified, compositional generation architecture that does not rely on pre-segmented inputs.
Neural Information Processing Systems
Jun-23-2026, 06:23:45 GMT
- Genre:
- Research Report
- Experimental Study (1.00)
- New Finding (0.67)
- Research Report
- Technology:
- Information Technology > Artificial Intelligence
- Vision (1.00)
- Machine Learning > Neural Networks (0.93)
- Natural Language > Large Language Model (0.68)
- Information Technology > Artificial Intelligence