DreamPartGen: Semantically Grounded Part-Level 3D Generation via Collaborative Latent Denoising
Not on the map. Why?
Abstract (arXiv)
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 facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 54 of its 62 references that are in the map. First posted on arXiv 19 Mar 2026.
Builds on
54 of 62 references.
References · 54
- 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
- 2025Qwen2.5-VL Technical Reportcited by 5,418
- 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
- 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,006
- 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
- 2024Gemma 2: Improving Open Language Models at a Practical Sizecited by 1,928
- 2022Objaverse: A Universe of Annotated 3D Objectscited by 1,522
- 2023Zero-1-to-3: Zero-shot One Image to 3D Objectcited by 1,483
- 2022Magic3D: High-Resolution Text-to-3D Content Creationcited by 1,285
- 2023ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillationcited by 1,207
- 2023MVDream: Multi-view Diffusion for 3D Generationcited by 928
- 2023PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesiscited by 854
38 more
- 2023DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creationcited by 837
- 2024Structured 3D Latents for Scalable and Versatile 3D Generationcited by 742
- 2023Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creationcited by 684
- 2018PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understandingcited by 521
- 20233DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Modelscited by 449
- 2024CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assetscited by 444
- 2021ABO: Dataset and Benchmarks for Real-World 3D Object Understandingcited by 360
- 2023LucidDreamer: Towards High-Fidelity Text-to-3D Generation via Interval Score Matchingcited by 290
- 2023Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and Memorycited by 288
- 2022ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understandingcited by 262
- 2023GaussianDreamer: Fast Generation from Text to 3D Gaussians by Bridging 2D and 3D Diffusion Modelscited by 255
- 2023DreamBooth3D: Subject-Driven Text-to-3D Generationcited by 235
- 2023RichDreamer: A Generalizable Normal-Depth Diffusion Model for Detail Richness in Text-to-3Dcited by 168
- 2023SweetDreamer: Aligning Geometric Priors in 2D Diffusion for Consistent Text-to-3Dcited by 134
- 2022PartSLIP: Low-Shot Part Segmentation for 3D Point Clouds via Pretrained Image-Language Modelscited by 117
- 2024MIDI: Multi-Instance Diffusion for Single Image to 3D Scene Generationcited by 113
- 2025PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformerscited by 78
- 2025ArtGS: Building Interactable Replicas of Complex Articulated Objects via Gaussian Splattingcited by 67
- 2023SALAD: Part-Level Latent Diffusion for 3D Shape Generation and Manipulationcited by 66
- 2024PartGen: Part-level 3D Generation and Reconstruction with Multi-View Diffusion Modelscited by 60
- 2025OmniPart: Part-Aware 3D Generation with Semantic Decoupling and Structural Cohesioncited by 60
- 2025HoloPart: Generative 3D Part Amodal Segmentationcited by 57
- 2024Part123: Part-aware 3D Reconstruction from a Single-view Imagecited by 54
- 2025Efficient Part-level 3D Object Generation via Dual Volume Packingcited by 47
- 2025Ultra3D: Efficient and High-Fidelity 3D Generation with Part Attentioncited by 43
- 2025X-Part: high fidelity and structure coherent shape decompositioncited by 42
- 2015Text to 3D Scene Generation with Rich Lexical Groundingcited by 36
- 2025AutoPartGen: Autogressive 3D Part Generation and Discoverycited by 33
- 2025From One to More: Contextual Part Latents for 3D Generationcited by 26
- 2025DreamArt: Generating Interactable Articulated Objects from a Single Imagecited by 25
- 2025GaussianArt: Unified Modeling of Geometry and Motion for Articulated Objectscited by 17
- 2025FullPart: Generating each 3D Part at Full Resolutioncited by 17
- 2025PartSAM: A Scalable Promptable Part Segmentation Model Trained on Native 3D Datacited by 15
- 2024PASTA: Controllable Part-Aware Shape Generation with Autoregressive Transformerscited by 14
- 2024PRIMA: Multi-Image Vision-Language Models for Reasoning Segmentationcited by 13
- 2024PARIS3D: Reasoning-based 3D Part Segmentation Using Large Multimodal Modelcited by 9
- 2025CoRe3D: Collaborative Reasoning as a Foundation for 3D Intelligencecited by 9
- 2025Counterfactual Segmentation Reasoning: Diagnosing and Mitigating Pixel-Grounding Hallucinationcited by 7
50 most cited of 54 All 54 (JSON)
Built on by
Citing papers per year: 2026: 2.
2 papers.