PRISM: Probabilistic Representation for Integrated Shape Modeling and Generation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916676038033408 |
|---|---|
| author | Cheng, Lei Saleh, Mahdi Cheng, Qing Sang, Lu Xu, Hongli Cremers, Daniel Tombari, Federico |
| author_facet | Cheng, Lei Saleh, Mahdi Cheng, Qing Sang, Lu Xu, Hongli Cremers, Daniel Tombari, Federico |
| contents | Despite the advancements in 3D full-shape generation, accurately modeling complex geometries and semantics of shape parts remains a significant challenge, particularly for shapes with varying numbers of parts. Current methods struggle to effectively integrate the contextual and structural information of 3D shapes into their generative processes. We address these limitations with PRISM, a novel compositional approach for 3D shape generation that integrates categorical diffusion models with Statistical Shape Models (SSM) and Gaussian Mixture Models (GMM). Our method employs compositional SSMs to capture part-level geometric variations and uses GMM to represent part semantics in a continuous space. This integration enables both high fidelity and diversity in generated shapes while preserving structural coherence. Through extensive experiments on shape generation and manipulation tasks, we demonstrate that our approach significantly outperforms previous methods in both quality and controllability of part-level operations. Our code will be made publicly available. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_04454 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | PRISM: Probabilistic Representation for Integrated Shape Modeling and Generation Cheng, Lei Saleh, Mahdi Cheng, Qing Sang, Lu Xu, Hongli Cremers, Daniel Tombari, Federico Computer Vision and Pattern Recognition Despite the advancements in 3D full-shape generation, accurately modeling complex geometries and semantics of shape parts remains a significant challenge, particularly for shapes with varying numbers of parts. Current methods struggle to effectively integrate the contextual and structural information of 3D shapes into their generative processes. We address these limitations with PRISM, a novel compositional approach for 3D shape generation that integrates categorical diffusion models with Statistical Shape Models (SSM) and Gaussian Mixture Models (GMM). Our method employs compositional SSMs to capture part-level geometric variations and uses GMM to represent part semantics in a continuous space. This integration enables both high fidelity and diversity in generated shapes while preserving structural coherence. Through extensive experiments on shape generation and manipulation tasks, we demonstrate that our approach significantly outperforms previous methods in both quality and controllability of part-level operations. Our code will be made publicly available. |
| title | PRISM: Probabilistic Representation for Integrated Shape Modeling and Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.04454 |