mlsanityData to 7 Oct 2026

3D Human Texture Estimation from a Single Image with Transformers

arXiv 2109.02563 ↗First posted 6 Sep 2021cs.CV cs.AI cs.GRcited by 35

Not on the map. Why?

Abstract (arXiv)

We propose a Transformer-based framework for 3D human texture estimation from a single image. The proposed Transformer is able to effectively exploit the global information of the input image, overcoming the limitations of existing methods that are solely based on convolutional neural networks. In addition, we also propose a mask-fusion strategy to combine the advantages of the RGB-based and texture-flow-based models. We further introduce a part-style loss to help reconstruct high-fidelity colors without introducing unpleasant artifacts. Extensive experiments demonstrate the effectiveness of the proposed method against state-of-the-art 3D human texture estimation approaches both quantitatively and qualitatively.

Key facts. Cited by 35 papers in the map (data through 7 Oct 2026). Builds on 47 of its 59 references that are in the map. First posted on arXiv 6 Sep 2021.

Builds on

47 of 59 references.

References · 47

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  5. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  6. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  7. 2020End-to-End Object Detection with Transformerscited by 7,384
  8. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  9. 2016Layer Normalizationcited by 5,579
  10. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  11. 2020Pre-Trained Image Processing Transformercited by 891
  12. 2017End-to-end Recovery of Human Shape and Posecited by 883
35 more
  1. 2019PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitizationcited by 818
  2. 2019Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loopcited by 625
  3. 2019VIBE: Video Inference for Human Body Pose and Shape Estimationcited by 615
  4. 2020PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitizationcited by 521
  5. 2017Beyond Part Models: Person Retrieval with Refined Part Pooling (and a Strong Convolutional Baseline)cited by 472
  6. 2017Neural 3D Mesh Renderercited by 437
  7. 2017Learning from Synthetic Humanscited by 358
  8. 2018Learning Category-Specific Mesh Reconstruction from Image Collectionscited by 317
  9. 2018Learning 3D Human Dynamics from Videocited by 315
  10. 2020ARCH: Animatable Reconstruction of Clothed Humanscited by 257
  11. 2017Pose Guided Person Image Generationcited by 251
  12. 2019Multi-Garment Net: Learning to Dress 3D People from Imagescited by 244
  13. 2018Video Based Reconstruction of 3D People Modelscited by 237
  14. 2020PaMIR: Parametric Model-Conditioned Implicit Representation for Image-based Human Reconstructioncited by 231
  15. 2019DeepHuman: 3D Human Reconstruction from a Single Imagecited by 182
  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. 2019Quadratic video interpolationcited by 143
  19. 2020Self-supervised Single-view 3D Reconstruction via Semantic Consistencycited by 127
  20. 2018Detailed Human Avatars from Monocular Videocited by 109
  21. 2020Shape and Viewpoint without Keypointscited by 92
  22. 2018Dense Pose Transfercited by 83
  23. 2019360-Degree Textures of People in Clothing from a Single Imagecited by 75
  24. 2018SiCloPe: Silhouette-Based Clothed Peoplecited by 68
  25. 20193DPeople: Modeling the Geometry of Dressed Humanscited by 58
  26. 2020Learning to Transfer Texture from Clothing Images to 3D Humanscited by 58
  27. 2019Torchreid: A Library for Deep Learning Person Re-Identification in Pytorchcited by 41
  28. 2020Robust 3D Self-portraits in Secondscited by 30
  29. 20203D Human Shape and Pose from a Single Low-Resolution Image with Self-Supervised Learningcited by 28
  30. 2020TexMesh: Reconstructing Detailed Human Texture and Geometry from RGB-D Videocited by 27
  31. 20213D Human Pose, Shape and Texture from Low-Resolution Images and Videoscited by 26
  32. 2020Reconstructing NBA Playerscited by 24
  33. 2019Re-Identification Supervised Texture Generationcited by 19
  34. 2018EANet: Enhancing Alignment for Cross-Domain Person Re-identificationcited by 16
  35. 2021Learning Spatial and Spatio-Temporal Pixel Aggregations for Image and Video Denoisingcited by 9

Built on by

Cited by year

Citing papers per year: 2021: 3; 2022: 11; 2023: 9; 2024: 8; 2025: 4.

35 papers.

Sort:

By area:

  1. 2022Multimodal Learning with Transformers: A Surveycited by 399
  2. 2021Video Frame Interpolation Transformercited by 122
  3. 2022HandOccNet: Occlusion-Robust 3D Hand Mesh Estimation Networkcited by 95
  4. 2023Paint-it: Text-to-Texture Synthesis via Deep Convolutional Texture Map Optimization and Physically-Based Renderingcited by 84
  5. 2022AvatarGen: A 3D Generative Model for Animatable Human Avatarscited by 59
  6. 2021Geometry-Guided Progressive NeRF for Generalizable and Efficient Neural Human Renderingcited by 46
  7. 2023Towards Garment Sewing Pattern Reconstruction from a Single Imagecited by 33
  8. 2023SMPLitex: A Generative Model and Dataset for 3D Human Texture Estimation from Single Imagecited by 30
  9. 2023DINAR: Diffusion Inpainting of Neural Textures for One-Shot Human Avatarscited by 28
  10. 2022Structured 3D Features for Reconstructing Controllable Avatarscited by 19
  11. 2023Generating Aligned Pseudo-Supervision from Non-Aligned Data for Image Restoration in Under-Display Cameracited by 16
  12. 2022MonoNHR: Monocular Neural Human Renderercited by 15
23 more
  1. 2023Human MotionFormer: Transferring Human Motions with Vision Transformerscited by 14
  2. 2024TexDreamer: Towards Zero-Shot High-Fidelity 3D Human Texture Generationcited by 14
  3. 2025AG-VPReID: A Challenging Large-Scale Benchmark for Aerial-Ground Video-based Person Re-Identificationcited by 12
  4. 2022BodyMap: Learning Full-Body Dense Correspondence Mapcited by 11
  5. 2022Human Image Generation: A Comprehensive Surveycited by 11
  6. 2024SMPLer: Taming Transformers for Monocular 3D Human Shape and Pose Estimationcited by 9
  7. 2023Generating Texture for 3D Human Avatar from a Single Image using Sampling and Refinement Networkscited by 8
  8. 2024UVMap-ID: A Controllable and Personalized UV Map Generative Modelcited by 7
  9. 20223D Magic Mirror: Clothing Reconstruction from a Single Image via a Causal Perspectivecited by 5
  10. 2024Synthesizing Moving People with 3D Controlcited by 5
  11. 2023Text-guided 3D Human Generation from 2D Collectionscited by 4
  12. 2024Learning Interaction-aware 3D Gaussian Splatting for One-shot Hand Avatarscited by 3
  13. 2021The Nuts and Bolts of Adopting Transformer in GANscited by 2
  14. 2022ReFu: Refine and Fuse the Unobserved View for Detail-Preserving Single-Image 3D Human Reconstructioncited by 2
  15. 2023Refining 3D Human Texture Estimation from a Single Imagecited by 2
  16. 2024Personalized 3D Human Pose and Shape Refinementcited by 2
  17. 2025SMPL-GPTexture: Dual-View 3D Human Texture Estimation using Text-to-Image Generation Modelscited by 2
  18. 2025PARTE: Part-Guided Texturing for 3D Human Reconstruction from a Single Imagecited by 2
  19. 2024COSMU: Complete 3D human shape from monocular unconstrained imagescited by 1
  20. 2022AvatarGen: a 3D Generative Model for Animatable Human Avatarscited by 0
  21. 2022Generalizable Person Re-Identification via Viewpoint Alignment and Fusioncited by 0
  22. 2024Revisiting the Role of Texture in 3D Person Re-identificationcited by 0
  23. 2025PoseGRAF: Geometric-Reinforced Adaptive Fusion for Monocular 3D Human Pose Estimationcited by 0