mlsanityData to 14 Oct 2026

High-fidelity 3D Human Digitization from Single 2K Resolution Images

arXiv 2303.15108 ↗First posted 27 Mar 2023cs.CVcited by 70

Not on the map. Why?

Abstract (arXiv)

High-quality 3D human body reconstruction requires high-fidelity and large-scale training data and appropriate network design that effectively exploits the high-resolution input images. To tackle these problems, we propose a simple yet effective 3D human digitization method called 2K2K, which constructs a large-scale 2K human dataset and infers 3D human models from 2K resolution images. The proposed method separately recovers the global shape of a human and its details. The low-resolution depth network predicts the global structure from a low-resolution image, and the part-wise image-to-normal network predicts the details of the 3D human body structure. The high-resolution depth network merges the global 3D shape and the detailed structures to infer the high-resolution front and back side depth maps. Finally, an off-the-shelf mesh generator reconstructs the full 3D human model, which are available at https://github.com/SangHunHan92/2K2K. In addition, we also provide 2,050 3D human models, including texture maps, 3D joints, and SMPL parameters for research purposes. In experiments, we demonstrate competitive performance over the recent works on various datasets.

Key facts. Cited by 70 papers in the map (data through 14 Oct 2026). Builds on 39 of its 61 references that are in the map. First posted on arXiv 27 Mar 2023.

Builds on

39 of 61 references.

References · 39

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
  3. 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,612
  4. 2018Attention U-Net: Learning Where to Look for the Pancreascited by 1,435
  5. 2016Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,064
  6. 2017End-to-end Recovery of Human Shape and Posecited by 885
  7. 2019PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitizationcited by 818
  8. 2018DensePose: Dense Human Pose Estimation In The Wildcited by 575
  9. 2020PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitizationcited by 521
  10. 2017Learning from Synthetic Humanscited by 359
  11. 2021ICON: Implicit Clothed humans Obtained from Normalscited by 283
  12. 2020ARCH: Animatable Reconstruction of Clothed Humanscited by 257
27 more
  1. 2021Function4D: Real-time Human Volumetric Capture from Very Sparse Consumer RGBD Sensorscited by 246
  2. 2020PaMIR: Parametric Model-Conditioned Implicit Representation for Image-based Human Reconstructioncited by 231
  3. 2021AGORA: Avatars in Geography Optimized for Regression Analysiscited by 205
  4. 2019DeepHuman: 3D Human Reconstruction from a Single Imagecited by 182
  5. 2021ARCH++: Animation-Ready Clothed Human Reconstruction Revisitedcited by 174
  6. 2019Learning to Reconstruct People in Clothing from a Single RGB Cameracited by 168
  7. 2019Tex2Shape: Detailed Full Human Body Geometry From a Single Imagecited by 166
  8. 2021SMPLicit: Topology-aware Generative Model for Clothed Peoplecited by 155
  9. 2018BodyNet: Volumetric Inference of 3D Human Body Shapescited by 141
  10. 2022Photorealistic Monocular 3D Reconstruction of Humans Wearing Clothingcited by 126
  11. 2022HuMMan: Multi-Modal 4D Human Dataset for Versatile Sensing and Modelingcited by 117
  12. 2020Geo-PIFu: Geometry and Pixel Aligned Implicit Functions for Single-view Human Reconstructioncited by 112
  13. 2017Detailed, accurate, human shape estimation from clothed 3D scan sequencescited by 89
  14. 2019Detailed Human Shape Estimation from a Single Image by Hierarchical Mesh Deformationcited by 71
  15. 2020SMPLpix: Neural Avatars from 3D Human Modelscited by 69
  16. 2018SiCloPe: Silhouette-Based Clothed Peoplecited by 68
  17. 2019Moulding Humans: Non-parametric 3D Human Shape Estimation from Single Imagescited by 67
  18. 2021DeepMultiCap: Performance Capture of Multiple Characters Using Sparse Multiview Camerascited by 67
  19. 2021OpenPifPaf: Composite Fields for Semantic Keypoint Detection and Spatio-Temporal Associationcited by 55
  20. 2021StereoPIFu: Depth Aware Clothed Human Digitization via Stereo Visioncited by 38
  21. 2019A Neural Network for Detailed Human Depth Estimation from a Single Imagecited by 21
  22. 2020Self-Supervised Human Depth Estimation from Monocular Videoscited by 17
  23. 2021Detailed Avatar Recovery from Single Imagecited by 16
  24. 2021Multi-person Implicit Reconstruction from a Single Imagecited by 13
  25. 2022Super-resolution 3D Human Shape from a Single Low-Resolution Imagecited by 6
  26. 2021Temporal Consistency Loss for High Resolution Textured and Clothed 3DHuman Reconstruction from Monocular Videocited by 3
  27. 2022Monocular Human Digitization via Implicit Re-projection Networkscited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 8; 2024: 21; 2025: 25; 2026: 16.

70 papers.

Sort:

By area:

  1. 2023SIFU: Side-view Conditioned Implicit Function for Real-world Usable Clothed Human Reconstructioncited by 77
  2. 2023SiTH: Single-view Textured Human Reconstruction with Image-Conditioned Diffusioncited by 72
  3. 2025LHM: Large Animatable Human Reconstruction Model from a Single Image in Secondscited by 61
  4. 2024IDOL: Instant Photorealistic 3D Human Creation from a Single Imagecited by 55
  5. 2023MVHumanNet: A Large-scale Dataset of Multi-view Daily Dressing Human Capturescited by 54
  6. 20244D-DRESS: A 4D Dataset of Real-world Human Clothing with Semantic Annotationscited by 54
  7. 2024HumanSplat: Generalizable Single-Image Human Gaussian Splatting with Structure Priorscited by 54
  8. 2024Human-3Diffusion: Realistic Avatar Creation via Explicit 3D Consistent Diffusion Modelscited by 44
  9. 2023AvatarBooth: High-Quality and Customizable 3D Human Avatar Generationcited by 37
  10. 2024GaussianBody: Clothed Human Reconstruction via 3d Gaussian Splattingcited by 36
  11. 2024AniGS: Animatable Gaussian Avatar from a Single Image with Inconsistent Gaussian Reconstructioncited by 36
  12. 2024PSHuman: Photorealistic Single-image 3D Human Reconstruction using Cross-Scale Multiview Diffusion and Explicit Remeshingcited by 23
38 more
  1. 2025GAS: Generative Avatar Synthesis from a Single Imagecited by 19
  2. 2024Gen-3Diffusion: Realistic Image-to-3D Generation via 2D & 3D Diffusion Synergycited by 16
  3. 2024Ultraman: Single Image 3D Human Reconstruction with Ultra Speed and Detailcited by 12
  4. 2024CanonicalFusion: Generating Drivable 3D Human Avatars from Multiple Imagescited by 12
  5. 2024Grounding Language in Multi-Perspective Referential Communicationcited by 12
  6. 2025SIGMAN:Scaling 3D Human Gaussian Generation with Millions of Assetscited by 12
  7. 2025SOAP: Style-Omniscient Animatable Portraitscited by 11
  8. 2025DAViD: Data-efficient and Accurate Vision Models from Synthetic Datacited by 11
  9. 2025UP2You: Fast Reconstruction of Yourself from Unconstrained Photo Collectionscited by 10
  10. 2025MVHumanNet++: A Large-scale Dataset of Multi-view Daily Dressing Human Captures with Richer Annotations for 3D Human Digitizationcited by 9
  11. 2025SyncHuman: Synchronizing 2D and 3D Generative Models for Single-view Human Reconstructioncited by 9
  12. 2023Human as Points: Explicit Point-based 3D Human Reconstruction from Single-view RGB Imagescited by 8
  13. 2025HumanGif: Single-View Human Diffusion with Generative Priorcited by 7
  14. 2023Joint2Human: High-quality 3D Human Generation via Compact Spherical Embedding of 3D Jointscited by 6
  15. 2024GeneMAN: Generalizable Single-Image 3D Human Reconstruction from Multi-Source Human Datacited by 6
  16. 2025LHM++: An Efficient Large Human Reconstruction Model for Pose-free Images to 3Dcited by 6
  17. 2023R2Human: Real-Time 3D Human Appearance Rendering from a Single Imagecited by 5
  18. 2024Synthesizing Moving People with 3D Controlcited by 5
  19. 2024Semantic Human Mesh Reconstruction with Texturescited by 5
  20. 2024X-Oscar: A Progressive Framework for High-quality Text-guided 3D Animatable Avatar Generationcited by 5
  21. 2024Human-VDM: Learning Single-Image 3D Human Gaussian Splatting from Video Diffusion Modelscited by 5
  22. 2024Multi-hypotheses Conditioned Point Cloud Diffusion for 3D Human Reconstruction from Occluded Imagescited by 5
  23. 2025DeClotH: Decomposable 3D Cloth and Human Body Reconstruction from a Single Imagecited by 4
  24. 2025SMPL Normal Map Is All You Need for Single-view Textured Human Reconstructioncited by 3
  25. 2025InfiniHuman: Infinite 3D Human Creation with Precise Controlcited by 3
  26. 2025Bringing Your Portrait to 3D Presencecited by 3
  27. 2026Zero-Shot Reconstruction of Animatable 3D Avatars with Cloth Dynamics from a Single Imagecited by 3
  28. 2024RCR: Robust Crowd Reconstruction with Upright Space from a Single Large-scene Imagecited by 2
  29. 2025GeoMan: Temporally Consistent Human Geometry Estimation using Image-to-Video Diffusioncited by 2
  30. 2025PARTE: Part-Guided Texturing for 3D Human Reconstruction from a Single Imagecited by 2
  31. 2025Snap-Snap: Taking Two Images to Reconstruct 3D Human Gaussians in Millisecondscited by 2
  32. 2025HART: Human Aligned Reconstruction Transformercited by 2
  33. 2026Real-Time Human Frontal View Synthesis from a Single Imagecited by 2
  34. 2026OmniFit: Multi-modal 3D Body Fitting via Scale-agnostic Dense Landmark Predictioncited by 2
  35. 2023Weakly-Supervised 3D Reconstruction of Clothed Humans via Normal Mapscited by 1
  36. 2024FAMOUS: High-Fidelity Monocular 3D Human Digitization Using View Synthesiscited by 1
  37. 2025AniGaussian: Animatable Gaussian Avatar with Pose-guided Deformationcited by 1
  38. 2025MVD-HuGaS: Human Gaussians from a Single Image via 3D Human Multi-view Diffusion Priorcited by 1

50 most cited of 70 All 70 (JSON)