mlsanityData to 7 Oct 2026

DINAR: Diffusion Inpainting of Neural Textures for One-Shot Human Avatars

arXiv 2303.09375 ↗First posted 16 Mar 2023cs.CVcited by 28

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

Abstract (arXiv)

We present DINAR, an approach for creating realistic rigged fullbody avatars from single RGB images. Similarly to previous works, our method uses neural textures combined with the SMPL-X body model to achieve photo-realistic quality of avatars while keeping them easy to animate and fast to infer. To restore the texture, we use a latent diffusion model and show how such model can be trained in the neural texture space. The use of the diffusion model allows us to realistically reconstruct large unseen regions such as the back of a person given the frontal view. The models in our pipeline are trained using 2D images and videos only. In the experiments, our approach achieves state-of-the-art rendering quality and good generalization to new poses and viewpoints. In particular, the approach improves state-of-the-art on the SnapshotPeople public benchmark.

Key facts. Cited by 28 papers in the map (data through 7 Oct 2026). Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models. Builds on 50 of its 66 references that are in the map. First posted on arXiv 16 Mar 2023.

Builds on

50 of 66 references.

Closest ancestors · 3

Same direction, newest first

  1. 2023TEXTure: Text-Guided Texturing of 3D Shapes3 Feb
  2. 2022Rodin: A Generative Model for Sculpting 3D Digital Avatars Using Diffusion12 Dec
  3. 2022RePaint: Inpainting using Denoising Diffusion Probabilistic Models24 Jan

Other references · 47

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  4. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  5. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  6. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  7. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  8. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  9. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  10. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,229
  11. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  12. 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,600
35 more
  1. 2021Image Super-Resolution via Iterative Refinementcited by 1,506
  2. 2021Palette: Image-to-Image Diffusion Modelscited by 1,296
  3. 2018Demystifying MMD GANscited by 1,268
  4. 2022Human Motion Diffusion Modelcited by 1,062
  5. 2019PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitizationcited by 818
  6. 2020Image Quality Assessment: Unifying Structure and Texture Similaritycited by 792
  7. 2022MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Modelcited by 768
  8. 2021Resolution-robust Large Mask Inpainting with Fourier Convolutionscited by 730
  9. 2018Which Training Methods for GANs do actually Converge?cited by 672
  10. 2017Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentationscited by 614
  11. 2020PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitizationcited by 521
  12. 2022HumanNeRF: Free-viewpoint Rendering of Moving People from Monocular Videocited by 483
  13. 2021Animatable Neural Radiance Fields for Modeling Dynamic Human Bodiescited by 361
  14. 2021ICON: Implicit Clothed humans Obtained from Normalscited by 283
  15. 2020ARCH: Animatable Reconstruction of Clothed Humanscited by 257
  16. 2021Function4D: Real-time Human Volumetric Capture from Very Sparse Consumer RGBD Sensorscited by 246
  17. 2022NeuMan: Neural Human Radiance Field from a Single Videocited by 244
  18. 2018Video Based Reconstruction of 3D People Modelscited by 237
  19. 2021SCANimate: Weakly Supervised Learning of Skinned Clothed Avatar Networkscited by 181
  20. 2021ARCH++: Animation-Ready Clothed Human Reconstruction Revisitedcited by 174
  21. 2022Photorealistic Monocular 3D Reconstruction of Humans Wearing Clothingcited by 126
  22. 2020Geo-PIFu: Geometry and Pixel Aligned Implicit Functions for Single-view Human Reconstructioncited by 112
  23. 2018Detailed Human Avatars from Monocular Videocited by 109
  24. 2019Graphonomy: Universal Human Parsing via Graph Transfer Learningcited by 81
  25. 2019360-Degree Textures of People in Clothing from a Single Imagecited by 75
  26. 2020SMPLpix: Neural Avatars from 3D Human Modelscited by 69
  27. 2021StylePeople: A Generative Model of Fullbody Human Avatarscited by 62
  28. 2022Drivable Volumetric Avatars using Texel-Aligned Featurescited by 62
  29. 2020ANR: Articulated Neural Rendering for Virtual Avatarscited by 55
  30. 2022InsetGAN for Full-Body Image Generationcited by 45
  31. 2022Diffusion Motion: Generate Text-Guided 3D Human Motion by Diffusion Modelcited by 41
  32. 20213D Human Texture Estimation from a Single Image with Transformerscited by 35
  33. 2022Structured 3D Features for Reconstructing Controllable Avatarscited by 19
  34. 2021FlipReID: Closing the Gap between Training and Inference in Person Re-Identificationcited by 16
  35. 2021Real-time RGBD-based Extended Body Pose Estimationcited by 12

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 11; 2024: 11; 2025: 5; 2026: 1.

28 papers.

Sort:

By area:

  1. 2023TeCH: Text-guided Reconstruction of Lifelike Clothed Humanscited by 104
  2. 2023Paint-it: Text-to-Texture Synthesis via Deep Convolutional Texture Map Optimization and Physically-Based Renderingcited by 84
  3. 2023SiTH: Single-view Textured Human Reconstruction with Image-Conditioned Diffusioncited by 72
  4. 2023On the Design Fundamentals of Diffusion Models: A Surveycited by 59
  5. 2024DreamMat: High-quality PBR Material Generation with Geometry- and Light-aware Diffusion Modelscited by 50
  6. 2023Deformable 3D Gaussian Splatting for Animatable Human Avatarscited by 44
  7. 2023DiffusionAvatars: Deferred Diffusion for High-fidelity 3D Head Avatarscited by 42
  8. 2023Disentangled Clothed Avatar Generation from Text Descriptionscited by 33
  9. 2024HAHA: Highly Articulated Gaussian Human Avatars with Textured Mesh Priorcited by 30
  10. 2023UniGS: Unified Representation for Image Generation and Segmentationcited by 29
  11. 2024OHTA: One-shot Hand Avatar via Data-driven Implicit Priorscited by 18
  12. 2024PrefPaint: Aligning Image Inpainting Diffusion Model with Human Preferencecited by 17
16 more
  1. 2024TexDreamer: Towards Zero-Shot High-Fidelity 3D Human Texture Generationcited by 14
  2. 2023Single Mesh Diffusion Models with Field Latents for Texture Generationcited by 11
  3. 2024Diffusion Models in 3D Vision: A Surveycited by 11
  4. 2023MoRF: Mobile Realistic Fullbody Avatars from a Monocular Videocited by 7
  5. 2024High Quality Human Image Animation using Regional Supervision and Motion Blur Conditioncited by 7
  6. 2024DiffBody: Diffusion-based Pose and Shape Editing of Human Imagescited by 6
  7. 2025WonderHuman: Hallucinating Unseen Parts in Dynamic 3D Human Reconstructioncited by 6
  8. 2024Semantic Human Mesh Reconstruction with Texturescited by 5
  9. 2025Dream, Lift, Animate: From Single Images to Animatable Gaussian Avatarscited by 4
  10. 2024Generalizable Neural Human Renderercited by 3
  11. 2024Learning Interaction-aware 3D Gaussian Splatting for One-shot Hand Avatarscited by 3
  12. 2025R3-Avatar: Record and Retrieve Temporal Codebook for Reconstructing Photorealistic Human Avatarscited by 3
  13. 2025Computationally Efficient Diffusion Models in Medical Imaging: A Comprehensive Reviewcited by 1
  14. 2025Frequency-Decomposed Avatar Representation for Varying Camera Distancescited by 1
  15. 2023Reality's Canvas, Language's Brush: Crafting 3D Avatars from Monocular Videocited by 0
  16. 2026PHAF-Personalized Hand Avatars in a Flashcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Morphable Diffusion: 3D-Consistent Diffusion for Single-image Avatar Creation
  2. 2023AvatarCraft: Transforming Text into Neural Human Avatars with Parameterized Shape and Pose Control
  3. 2024HR Human: Modeling Human Avatars with Triangular Mesh and High-Resolution Textures from Videos
  4. 2023AvatarFusion: Zero-shot Generation of Clothing-Decoupled 3D Avatars Using 2D Diffusion
  5. 2025Hyper Diffusion Avatars: Dynamic Human Avatar Generation using Network Weight Space Diffusion
  6. 2024Human-3Diffusion: Realistic Avatar Creation via Explicit 3D Consistent Diffusion Models
  7. 2026GenLCA: 3D Diffusion for Full-Body Avatars from In-the-Wild Videos
  8. 2024Instant 3D Human Avatar Generation using Image Diffusion Models