ClotheDreamer: Text-Guided Garment Generation with 3D Gaussians
Not on the map. Why?
Abstract (arXiv)
High-fidelity 3D garment synthesis from text is desirable yet challenging for digital avatar creation. Recent diffusion-based approaches via Score Distillation Sampling (SDS) have enabled new possibilities but either intricately couple with human body or struggle to reuse. We introduce ClotheDreamer, a 3D Gaussian-based method for generating wearable, production-ready 3D garment assets from text prompts. We propose a novel representation Disentangled Clothe Gaussian Splatting (DCGS) to enable separate optimization. DCGS represents clothed avatar as one Gaussian model but freezes body Gaussian splats. To enhance quality and completeness, we incorporate bidirectional SDS to supervise clothed avatar and garment RGBD renderings respectively with pose conditions and propose a new pruning strategy for loose clothing. Our approach can also support custom clothing templates as input. Benefiting from our design, the synthetic 3D garment can be easily applied to virtual try-on and support physically accurate animation. Extensive experiments showcase our method's superior and competitive performance. Our project page is at https://ggxxii.github.io/clothedreamer.
Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 68 of its 87 references that are in the map. First posted on arXiv 24 Jun 2024.
Builds on
68 of 87 references.
References · 68
- 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
- 2022Training language models to follow instructions with human feedbackcited by 15,712
- 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
- 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,006
- 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,701
- 2021Plenoxels: Radiance Fields without Neural Networkscited by 1,607
- 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,600
- 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
- 2023DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creationcited by 837
- 2024LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creationcited by 730
- 2022Point-E: A System for Generating 3D Point Clouds from Complex Promptscited by 694
38 more
- 2023Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creationcited by 684
- 2021Deep Marching Tetrahedra: a Hybrid Representation for High-Resolution 3D Shape Synthesiscited by 459
- 2022GET3D: A Generative Model of High Quality 3D Textured Shapes Learned from Imagescited by 446
- 2023Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priorscited by 395
- 2023Shap-E: Generating Conditional 3D Implicit Functionscited by 379
- 2023Make-It-3D: High-Fidelity 3D Creation from A Single Image with Diffusion Priorcited by 341
- 2021Text2Mesh: Text-Driven Neural Stylization for Meshescited by 332
- 2023Common Diffusion Noise Schedules and Sample Steps are Flawedcited by 308
- 2023Text-to-3D using Gaussian Splattingcited by 299
- 2023LucidDreamer: Towards High-Fidelity Text-to-3D Generation via Interval Score Matchingcited by 290
- 2023GaussianDreamer: Fast Generation from Text to 3D Gaussians by Bridging 2D and 3D Diffusion Modelscited by 255
- 2023GaussianShader: 3D Gaussian Splatting with Shading Functions for Reflective Surfacescited by 249
- 2023MVDiffusion: Enabling Holistic Multi-view Image Generation with Correspondence-Aware Diffusioncited by 210
- 2021SMPLicit: Topology-aware Generative Model for Clothed Peoplecited by 154
- 2023DreamAvatar: Text-and-Shape Guided 3D Human Avatar Generation via Diffusion Modelscited by 154
- 2022EVA3D: Compositional 3D Human Generation from 2D Image Collectionscited by 111
- 2023TADA! Text to Animatable Digital Avatarscited by 109
- 2023HoloDiffusion: Training a 3D Diffusion Model using 2D Imagescited by 106
- 2023DreamHuman: Animatable 3D Avatars from Textcited by 102
- 2023Noise-Free Score Distillationcited by 99
- 2018DeepWrinkles: Accurate and Realistic Clothing Modelingcited by 90
- 2023HumanGaussian: Text-Driven 3D Human Generation with Gaussian Splattingcited by 89
- 2023HumanNorm: Learning Normal Diffusion Model for High-quality and Realistic 3D Human Generationcited by 88
- 2020SIZER: A Dataset and Model for Parsing 3D Clothing and Learning Size Sensitive 3D Clothingcited by 87
- 2023AvatarCraft: Transforming Text into Neural Human Avatars with Parameterized Shape and Pose Controlcited by 84
- 2022SNUG: Self-Supervised Neural Dynamic Garmentscited by 83
- 2023DreamWaltz: Make a Scene with Complex 3D Animatable Avatarscited by 82
- 2022HOOD: Hierarchical Graphs for Generalized Modelling of Clothing Dynamicscited by 77
- 2018GarNet: A Two-Stream Network for Fast and Accurate 3D Cloth Drapingcited by 69
- 2020PBNS: Physically Based Neural Simulator for Unsupervised Garment Pose Space Deformationcited by 63
- 2023GAvatar: Animatable 3D Gaussian Avatars with Implicit Mesh Learningcited by 63
- 2022AvatarCLIP: Zero-Shot Text-Driven Generation and Animation of 3D Avatarscited by 55
- 2020DeepCloth: Neural Garment Representation for Shape and Style Editingcited by 54
- 2018Learning a Shared Shape Space for Multimodal Garment Designcited by 52
- 2020DeePSD: Automatic Deep Skinning And Pose Space Deformation For 3D Garment Animationcited by 43
- 2024DressCode: Autoregressively Sewing and Generating Garments from Text Guidancecited by 43
- 2023DiffAvatar: Simulation-Ready Garment Optimization with Differentiable Simulationcited by 40
- 2022Predicting Loose-Fitting Garment Deformations Using Bone-Driven Motion Networkscited by 39
50 most cited of 68 All 68 (JSON)
Built on by
Citing papers per year: 2024: 1; 2025: 5; 2026: 3.
9 papers.
- 2025Disentangled Clothed Avatar Generation with Layered Representationcited by 7
- 2024DreamBarbie: Text to Barbie-Style 3D Avatarscited by 4
- 2025GarmageNet: A Multimodal Generative Framework for Sewing Pattern Design and Generic Garment Modelingcited by 4
- 2025GarmentX: Autoregressive Parametric Representations for High-Fidelity 3D Garment Generationcited by 3
- 2026PatternGSL: A Structured Specification Language for Template-Free and Simulation-Ready 3D Garmentscited by 1
- 2025GaussianIP: Identity-Preserving Realistic 3D Human Generation via Human-Centric Diffusion Priorcited by 0
- 2025Avatar4D: Synthesizing Domain-Specific 4D Humans for Real-World Pose Estimationcited by 0
- 2026CausalGS: Learning Physical Causality of 3D Dynamic Scenes with Gaussian Representationscited by 0
- 2026Stitched Embeddings: A Unified Latent Space for 3D Garments and 2D Patternscited by 0
- 2026Stitched Embeddings: A Unified Latent Space for 3D Garments and 2D Patterns1 Jul 2026
- 2026PatternGSL: A Structured Specification Language for Template-Free and Simulation-Ready 3D Garments23 Jun 2026
- 2026CausalGS: Learning Physical Causality of 3D Dynamic Scenes with Gaussian Representations11 May 2026
- 2025Avatar4D: Synthesizing Domain-Specific 4D Humans for Real-World Pose Estimation18 Dec 2025
- 2025GarmentX: Autoregressive Parametric Representations for High-Fidelity 3D Garment Generation29 Apr 2025
- 2025GarmageNet: A Multimodal Generative Framework for Sewing Pattern Design and Generic Garment Modeling2 Apr 2025
- 2025GaussianIP: Identity-Preserving Realistic 3D Human Generation via Human-Centric Diffusion Prior14 Mar 2025
- 2025Disentangled Clothed Avatar Generation with Layered Representation8 Jan 2025
- 2024DreamBarbie: Text to Barbie-Style 3D Avatars17 Aug 2024