mlsanityData to 14 Oct 2026

Super-resolution 3D Human Shape from a Single Low-Resolution Image

arXiv 2208.10738 ↗First posted 23 Aug 2022cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

We propose a novel framework to reconstruct super-resolution human shape from a single low-resolution input image. The approach overcomes limitations of existing approaches that reconstruct 3D human shape from a single image, which require high-resolution images together with auxiliary data such as surface normal or a parametric model to reconstruct high-detail shape. The proposed framework represents the reconstructed shape with a high-detail implicit function. Analogous to the objective of 2D image super-resolution, the approach learns the mapping from a low-resolution shape to its high-resolution counterpart and it is applied to reconstruct 3D shape detail from low-resolution images. The approach is trained end-to-end employing a novel loss function which estimates the information lost between a low and high-resolution representation of the same 3D surface shape. Evaluation for single image reconstruction of clothed people demonstrates that our method achieves high-detail surface reconstruction from low-resolution images without auxiliary data. Extensive experiments show that the proposed approach can estimate super-resolution human geometries with a significantly higher level of detail than that obtained with previous approaches when applied to low-resolution images.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 37 of its 56 references that are in the map. First posted on arXiv 23 Aug 2022.

Builds on

37 of 56 references.

References · 37

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  2. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
  3. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,041
  4. 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,612
  5. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  6. 2016Stacked Hourglass Networks for Human Pose Estimationcited by 915
  7. 2017End-to-end Recovery of Human Shape and Posecited by 885
  8. 2019PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitizationcited by 818
  9. 2016Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Imagecited by 695
  10. 2019VIBE: Video Inference for Human Body Pose and Shape Estimationcited by 620
  11. 2020PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitizationcited by 521
  12. 2019Deep Learning for Image Super-resolution: A Surveycited by 369
25 more
  1. 2020ARCH: Animatable Reconstruction of Clothed Humanscited by 257
  2. 2021Function4D: Real-time Human Volumetric Capture from Very Sparse Consumer RGBD Sensorscited by 246
  3. 2018Video Based Reconstruction of 3D People Modelscited by 238
  4. 2020PaMIR: Parametric Model-Conditioned Implicit Representation for Image-based Human Reconstructioncited by 231
  5. 2019DeepHuman: 3D Human Reconstruction from a Single Imagecited by 182
  6. 2021ARCH++: Animation-Ready Clothed Human Reconstruction Revisitedcited by 174
  7. 2019Learning to Reconstruct People in Clothing from a Single RGB Cameracited by 168
  8. 2019Tex2Shape: Detailed Full Human Body Geometry From a Single Imagecited by 166
  9. 2018BodyNet: Volumetric Inference of 3D Human Body Shapescited by 141
  10. 2020Unfolding the Alternating Optimization for Blind Super Resolutioncited by 129
  11. 2020Geo-PIFu: Geometry and Pixel Aligned Implicit Functions for Single-view Human Reconstructioncited by 112
  12. 2020Channel Attention based Iterative Residual Learning for Depth Map Super-Resolutioncited by 40
  13. 2021StereoPIFu: Depth Aware Clothed Human Digitization via Stereo Visioncited by 38
  14. 2017SurfNet: Generating 3D shape surfaces using deep residual networkscited by 32
  15. 20183D Human Body Reconstruction from a Single Image via Volumetric Regressioncited by 29
  16. 20213D Human Pose, Shape and Texture from Low-Resolution Images and Videoscited by 26
  17. 2017Light Field Super-Resolution Via Graph-Based Regularizationcited by 15
  18. 2019Point Cloud Super Resolution with Adversarial Residual Graph Networkscited by 13
  19. 2021Attention-based Multi-Reference Learning for Image Super-Resolutioncited by 12
  20. 20193D Appearance Super-Resolution with Deep Learningcited by 11
  21. 2021Data-Driven 3D Reconstruction of Dressed Humans From Sparse Viewscited by 11
  22. 2019Inferring Super-Resolution Depth from a Moving Light-Source Enhanced RGB-D Sensor: A Variational Approachcited by 8
  23. 2020Learned Multi-View Texture Super-Resolutioncited by 7
  24. 2020Detailed 3D Human Body Reconstruction from Multi-view Images Combining Voxel Super-Resolution and Learned Implicit Representationcited by 6
  25. 2021Super-Resolution Appearance Transfer for 4D Human Performancescited by 1

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 3; 2025: 1.

6 papers.

  1. 2023High-fidelity 3D Human Digitization from Single 2K Resolution Imagescited by 70
  2. 2024ANIM: Accurate Neural Implicit Model for Human Reconstruction from a single RGB-D imagecited by 9
  3. 2023HISR: Hybrid Implicit Surface Representation for Photorealistic 3D Human Reconstructioncited by 1
  4. 2024COSMU: Complete 3D human shape from monocular unconstrained imagescited by 1
  5. 2024InstantGeoAvatar: Effective Geometry and Appearance Modeling of Animatable Avatars from Monocular Videocited by 0
  6. 2025Realistic Clothed Human and Object Joint Reconstruction from a Single Imagecited by 0