mlsanityData to 14 Oct 2026

AvatarStudio: High-fidelity and Animatable 3D Avatar Creation from Text

arXiv 2311.17917 ↗First posted 29 Nov 2023cs.GR cs.CVcited by 16

On the map: Diffusion models → 3D, point cloud and scene generation

Abstract (arXiv)

We study the problem of creating high-fidelity and animatable 3D avatars from only textual descriptions. Existing text-to-avatar methods are either limited to static avatars which cannot be animated or struggle to generate animatable avatars with promising quality and precise pose control. To address these limitations, we propose AvatarStudio, a coarse-to-fine generative model that generates explicit textured 3D meshes for animatable human avatars. Specifically, AvatarStudio begins with a low-resolution NeRF-based representation for coarse generation, followed by incorporating SMPL-guided articulation into the explicit mesh representation to support avatar animation and high resolution rendering. To ensure view consistency and pose controllability of the resulting avatars, we introduce a 2D diffusion model conditioned on DensePose for Score Distillation Sampling supervision. By effectively leveraging the synergy between the articulated mesh representation and the DensePose-conditional diffusion model, AvatarStudio can create high-quality avatars from text that are ready for animation, significantly outperforming previous methods. Moreover, it is competent for many applications, e.g., multimodal avatar animations and style-guided avatar creation. For more results, please refer to our project page: http://jeff95.me/projects/avatarstudio.html

Key facts. Cited by 16 papers in the map (data through 14 Oct 2026). Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models. Builds on 44 of its 54 references that are in the map. First posted on arXiv 29 Nov 2023.

Builds on

44 of 54 references.

Closest ancestors · 8

Same direction, newest first

  1. 2023HumanNorm: Learning Normal Diffusion Model for High-quality and Realistic 3D Human Generation2 Oct
  2. 2023MVDream: Multi-view Diffusion for 3D Generation31 Aug
  3. 2023ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation25 May
  4. 2023DreamAvatar: Text-and-Shape Guided 3D Human Avatar Generation via Diffusion Models3 Apr
  5. 2023Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creation24 Mar
  6. 2023TEXTure: Text-Guided Texturing of 3D Shapes3 Feb
  7. 2022Magic3D: High-Resolution Text-to-3D Content Creation18 Nov
  8. 2022DreamFusion: Text-to-3D using 2D Diffusion29 Sep

Other references · 36

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  4. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,355
  5. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  6. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,503
  7. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,152
  8. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,723
  9. 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,612
  10. 2023IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Modelscited by 1,464
  11. 2021Palette: Image-to-Image Diffusion Modelscited by 1,300
  12. 2022Human Motion Diffusion Modelcited by 1,080
24 more
  1. 2018DensePose: Dense Human Pose Estimation In The Wildcited by 575
  2. 2021Zero-Shot Text-Guided Object Generation with Dream Fieldscited by 513
  3. 2022Latent-NeRF for Shape-Guided Generation of 3D Shapes and Texturescited by 506
  4. 2021Deep Marching Tetrahedra: a Hybrid Representation for High-Resolution 3D Shape Synthesiscited by 460
  5. 2020Modular Primitives for High-Performance Differentiable Renderingcited by 441
  6. 2021PARE: Part Attention Regressor for 3D Human Body Estimationcited by 337
  7. 2023Common Diffusion Noise Schedules and Sample Steps are Flawedcited by 310
  8. 2020HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimationcited by 307
  9. 2022CLIP-Mesh: Generating textured meshes from text using pretrained image-text modelscited by 281
  10. 2021CLIP-Forge: Towards Zero-Shot Text-to-Shape Generationcited by 254
  11. 2022VoxGRAF: Fast 3D-Aware Image Synthesis with Sparse Voxel Gridscited by 133
  12. 2022EVA3D: Compositional 3D Human Generation from 2D Image Collectionscited by 111
  13. 2023TADA! Text to Animatable Digital Avatarscited by 110
  14. 2021Animatable Neural Radiance Fields from Monocular RGB Videoscited by 109
  15. 2021imGHUM: Implicit Generative Models of 3D Human Shape and Articulated Posecited by 103
  16. 2023DreamHuman: Animatable 3D Avatars from Textcited by 102
  17. 2023AvatarCraft: Transforming Text into Neural Human Avatars with Parameterized Shape and Pose Controlcited by 84
  18. 2023DreamWaltz: Make a Scene with Complex 3D Animatable Avatarscited by 82
  19. 2021Geometry-Consistent Neural Shape Representation with Implicit Displacement Fieldscited by 60
  20. 2023AvatarVerse: High-quality & Stable 3D Avatar Creation from Text and Posecited by 60
  21. 2022AvatarGen: A 3D Generative Model for Animatable Human Avatarscited by 59
  22. 2022AvatarCLIP: Zero-Shot Text-Driven Generation and Animation of 3D Avatarscited by 55
  23. 2023GETAvatar: Generative Textured Meshes for Animatable Human Avatarscited by 27
  24. 2023XAGen: 3D Expressive Human Avatars Generationcited by 17

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 13; 2025: 2.

16 papers.

Sort:

By area:

  1. 2024Advances in 3D Generation: A Surveycited by 63
  2. 2024HeadStudio: Text to Animatable Head Avatars with 3D Gaussian Splattingcited by 35
  3. 2023Disentangled Clothed Avatar Generation from Text Descriptionscited by 33
  4. 2024CharacterGen: Efficient 3D Character Generation from Single Images with Multi-View Pose Canonicalizationcited by 28
  5. 2024Connecting Consistency Distillation to Score Distillation for Text-to-3D Generationcited by 18
  6. 2024Portrait3D: Text-Guided High-Quality 3D Portrait Generation Using Pyramid Representation and GANs Priorcited by 15
  7. 2024Instant 3D Human Avatar Generation using Image Diffusion Modelscited by 14
  8. 2024STAR: Skeleton-aware Text-based 4D Avatar Generation with In-Network Motion Retargetingcited by 13
  9. 2024Envision3D: One Image to 3D with Anchor Views Interpolationcited by 12
  10. 2024HeadEvolver: Text to Head Avatars via Expressive and Attribute-Preserving Mesh Deformationcited by 11
  11. 2024X-Oscar: A Progressive Framework for High-quality Text-guided 3D Animatable Avatar Generationcited by 5
  12. 2024DreamBarbie: Text to Barbie-Style 3D Avatarscited by 4
4 more
  1. 2025PoseMaster: A Unified 3D Native Framework for Stylized Pose Generationcited by 3
  2. 2025Text-based Animatable 3D Avatars with Morphable Model Alignmentcited by 2
  3. 2024Avatar Concept Slider: Controllable Editing of Concepts in 3D Human Avatarscited by 1
  4. 2024DivAvatar: Diverse 3D Avatar Generation with a Single Promptcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023AvatarBooth: High-Quality and Customizable 3D Human Avatar Generation
  2. 2024DreamWaltz-G: Expressive 3D Gaussian Avatars from Skeleton-Guided 2D Diffusion
  3. 2023Guide3D: Create 3D Avatars from Text and Image Guidance
  4. 2024Morphable Diffusion: 3D-Consistent Diffusion for Single-image Avatar Creation
  5. 2023AvatarStudio: Text-driven Editing of 3D Dynamic Human Head Avatars
  6. 2025GAS: Generative Avatar Synthesis from a Single Image
  7. 2025AdaHuman: Animatable Detailed 3D Human Generation with Compositional Multiview Diffusion
  8. 2023Articulated 3D Head Avatar Generation using Text-to-Image Diffusion Models