[Paper] DreamPartGen: Semantically Grounded Part-Level 3D Generation via Collaborative Latent Denoising

Source: arXiv - 2603.19216v1

Overview

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.

Key Contributions

This paper presents research in the following areas:

• cs.CV
• cs.AI
• cs.LG

Methodology

Please refer to the full paper for detailed methodology.

Practical Implications

This research contributes to the advancement of cs.CV.

Authors

• Tianjiao Yu
• Xinzhuo Li
• Muntasir Wahed
• Jerry Xiong
• Yifan Shen
• Ying Shen
• Ismini Lourentzou

Paper Information

• arXiv ID: 2603.19216v1
• Categories: cs.CV, cs.AI, cs.LG
• Published: March 19, 2026
• PDF: Download PDF