mlsanityData to 14 Oct 2026

Detailed Avatar Recovery from Single Image

arXiv 2108.02931 ↗First posted 6 Aug 2021cs.CVcited by 16

Not on the map. Why?

Abstract (arXiv)

This paper presents a novel framework to recover detailed avatar from a single image. It is a challenging task due to factors such as variations in human shapes, body poses, texture, and viewpoints. Prior methods typically attempt to recover the human body shape using a parametric-based template that lacks the surface details. As such resulting body shape appears to be without clothing. In this paper, we propose a novel learning-based framework that combines the robustness of the parametric model with the flexibility of free-form 3D deformation. We use the deep neural networks to refine the 3D shape in a Hierarchical Mesh Deformation (HMD) framework, utilizing the constraints from body joints, silhouettes, and per-pixel shading information. Our method can restore detailed human body shapes with complete textures beyond skinned models. Experiments demonstrate that our method has outperformed previous state-of-the-art approaches, achieving better accuracy in terms of both 2D IoU number and 3D metric distance.

Key facts. Cited by 16 papers in the map (data through 14 Oct 2026). Builds on 52 of its 82 references that are in the map. First posted on arXiv 6 Aug 2021.

Builds on

52 of 82 references.

References · 52

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  4. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,527
  5. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,694
  6. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,636
  7. 2015Spatial Transformer Networkscited by 1,429
  8. 2017End-to-end Recovery of Human Shape and Posecited by 885
  9. 2019PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitizationcited by 818
  10. 2016Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Imagecited by 695
  11. 2018Generative Image Inpainting with Contextual Attentioncited by 580
  12. 2018DensePose: Dense Human Pose Estimation In The Wildcited by 575
38 more
  1. 2020PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitizationcited by 521
  2. 2017Learning from Synthetic Humanscited by 359
  3. 2018Learning 3D Human Dynamics from Videocited by 316
  4. 2019Convolutional Mesh Regression for Single-Image Human Shape Reconstructioncited by 270
  5. 2020ARCH: Animatable Reconstruction of Clothed Humanscited by 257
  6. 2019Multi-Garment Net: Learning to Dress 3D People from Imagescited by 245
  7. 2018Video Based Reconstruction of 3D People Modelscited by 238
  8. 2020PaMIR: Parametric Model-Conditioned Implicit Representation for Image-based Human Reconstructioncited by 231
  9. 2018Learning to Estimate 3D Human Pose and Shape from a Single Color Imagecited by 226
  10. 2016Generating Images with Perceptual Similarity Metrics based on Deep Networkscited by 222
  11. 2017Unite the People: Closing the Loop Between 3D and 2D Human Representationscited by 205
  12. 2018Neural Body Fitting: Unifying Deep Learning and Model-Based Human Pose and Shape Estimationcited by 185
  13. 2019DeepHuman: 3D Human Reconstruction from a Single Imagecited by 182
  14. 2016EnhanceNet: Single Image Super-Resolution Through Automated Texture Synthesiscited by 178
  15. 2016View Synthesis by Appearance Flowcited by 172
  16. 2019Learning to Reconstruct People in Clothing from a Single RGB Cameracited by 168
  17. 2019Tex2Shape: Detailed Full Human Body Geometry From a Single Imagecited by 166
  18. 2019EdgeConnect: Generative Image Inpainting with Adversarial Edge Learningcited by 163
  19. 2018BodyNet: Volumetric Inference of 3D Human Body Shapescited by 141
  20. 2017SfSNet: Learning Shape, Reflectance and Illuminance of Faces in the Wildcited by 110
  21. 2019Dense Intrinsic Appearance Flow for Human Pose Transfercited by 104
  22. 2017Self-supervised Learning of Motion Capturecited by 97
  23. 2017Detailed, accurate, human shape estimation from clothed 3D scan sequencescited by 89
  24. 2018Shift-Net: Image Inpainting via Deep Feature Rearrangementcited by 87
  25. 2018Dense Pose Transfercited by 83
  26. 2019360-Degree Textures of People in Clothing from a Single Imagecited by 75
  27. 2020Monocular Real-Time Volumetric Performance Capturecited by 74
  28. 2019Detailed Human Shape Estimation from a Single Image by Hierarchical Mesh Deformationcited by 71
  29. 2018SiCloPe: Silhouette-Based Clothed Peoplecited by 68
  30. 2017Transformation-Grounded Image Generation Network for Novel 3D View Synthesiscited by 59
  31. 2020Learning to Transfer Texture from Clothing Images to 3D Humanscited by 58
  32. 2019SimulCap : Single-View Human Performance Capture with Cloth Simulationcited by 41
  33. 2019FACSIMILE: Fast and Accurate Scans From an Image in Less Than a Secondcited by 35
  34. 2018DenseReg: Fully Convolutional Dense Shape Regression In-the-Wildcited by 32
  35. 2019A Neural Network for Detailed Human Depth Estimation from a Single Imagecited by 21
  36. 2020Self-Supervised Human Depth Estimation from Monocular Videoscited by 17
  37. 2016General Automatic Human Shape and Motion Capture Using Volumetric Contour Cuescited by 15
  38. 2016Model-based Outdoor Performance Capturecited by 13

50 most cited of 52 All 52 (JSON)

Built on by

Cited by year

Citing papers per year: 2021: 2; 2022: 4; 2023: 3; 2024: 5; 2025: 2.

16 papers.

Sort:

By area:

  1. 2023High-fidelity 3D Human Digitization from Single 2K Resolution Imagescited by 70
  2. 2021EventHPE: Event-based 3D Human Pose and Shape Estimationcited by 42
  3. 2023AvatarBooth: High-Quality and Customizable 3D Human Avatar Generationcited by 37
  4. 2022FOF: Learning Fourier Occupancy Field for Monocular Real-time Human Reconstructioncited by 27
  5. 2022Learnable human mesh triangulation for 3D human pose and shape estimationcited by 16
  6. 2022Detailed Facial Geometry Recovery from Multi-View Images by Learning an Implicit Functioncited by 14
  7. 2021Human Pose and Shape Estimation from Single Polarization Imagescited by 13
  8. 2024Deep learning for 3D human pose estimation and mesh recovery: A surveycited by 11
  9. 2023RAFaRe: Learning Robust and Accurate Non-parametric 3D Face Reconstruction from Pseudo 2D&3D Pairscited by 6
  10. 2024Semantic Human Mesh Reconstruction with Texturescited by 5
  11. 2025TeRA: Rethinking Text-guided Realistic 3D Avatar Generationcited by 5
  12. 2025Sketch2PoseNet: Efficient and Generalized Sketch to 3D Human Pose Predictioncited by 2
4 more
  1. 2022Monocular Human Digitization via Implicit Re-projection Networkscited by 1
  2. 2024D-PoSE: Depth as an Intermediate Representation for 3D Human Pose and Shape Estimationcited by 1
  3. 2024FOF-X: Towards Real-time Detailed Human Reconstruction from a Single Imagecited by 1
  4. 2024Mesh deformation-based single-view 3D reconstruction of thin eyeglasses frames with differentiable renderingcited by 0