DreamPartGen: Semantically Grounded Part-Level 3D Generation via Collaborative Latent Denoising
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912974581530624 |
|---|---|
| author | Yu, Tianjiao Li, Xinzhuo Wahed, Muntasir Xiong, Jerry Shen, Yifan Shen, Ying Lourentzou, Ismini |
| author_facet | Yu, Tianjiao Li, Xinzhuo Wahed, Muntasir Xiong, Jerry Shen, Yifan Shen, Ying Lourentzou, Ismini |
| contents | Understanding and generating 3D objects as compositions of meaningful parts is fundamental to human perception and reasoning. However, most text-to-3D methods overlook the semantic and functional structure of parts. While recent part-aware approaches introduce decomposition, they remain largely geometry-focused, lacking semantic grounding and failing to model how parts align with textual descriptions or their inter-part relations. We propose DreamPartGen, a framework for semantically grounded, part-aware text-to-3D generation. DreamPartGen introduces Duplex Part Latents (DPLs) that jointly model each part's geometry and appearance, and Relational Semantic Latents (RSLs) that capture inter-part dependencies derived from language. A synchronized co-denoising process enforces mutual geometric and semantic consistency, enabling coherent, interpretable, and text-aligned 3D synthesis. Across multiple benchmarks, DreamPartGen delivers state-of-the-art performance in geometric fidelity and text-shape alignment. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_19216 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | DreamPartGen: Semantically Grounded Part-Level 3D Generation via Collaborative Latent Denoising Yu, Tianjiao Li, Xinzhuo Wahed, Muntasir Xiong, Jerry Shen, Yifan Shen, Ying Lourentzou, Ismini Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Understanding and generating 3D objects as compositions of meaningful parts is fundamental to human perception and reasoning. However, most text-to-3D methods overlook the semantic and functional structure of parts. While recent part-aware approaches introduce decomposition, they remain largely geometry-focused, lacking semantic grounding and failing to model how parts align with textual descriptions or their inter-part relations. We propose DreamPartGen, a framework for semantically grounded, part-aware text-to-3D generation. DreamPartGen introduces Duplex Part Latents (DPLs) that jointly model each part's geometry and appearance, and Relational Semantic Latents (RSLs) that capture inter-part dependencies derived from language. A synchronized co-denoising process enforces mutual geometric and semantic consistency, enabling coherent, interpretable, and text-aligned 3D synthesis. Across multiple benchmarks, DreamPartGen delivers state-of-the-art performance in geometric fidelity and text-shape alignment. |
| title | DreamPartGen: Semantically Grounded Part-Level 3D Generation via Collaborative Latent Denoising |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2603.19216 |