mlsanityData to 14 Oct 2026

Photorealistic Monocular 3D Reconstruction of Humans Wearing Clothing

arXiv 2204.08906 ↗First posted 19 Apr 2022cs.CVcited by 126

Not on the map. Why?

Abstract (arXiv)

We present PHORHUM, a novel, end-to-end trainable, deep neural network methodology for photorealistic 3D human reconstruction given just a monocular RGB image. Our pixel-aligned method estimates detailed 3D geometry and, for the first time, the unshaded surface color together with the scene illumination. Observing that 3D supervision alone is not sufficient for high fidelity color reconstruction, we introduce patch-based rendering losses that enable reliable color reconstruction on visible parts of the human, and detailed and plausible color estimation for the non-visible parts. Moreover, our method specifically addresses methodological and practical limitations of prior work in terms of representing geometry, albedo, and illumination effects, in an end-to-end model where factors can be effectively disentangled. In extensive experiments, we demonstrate the versatility and robustness of our approach. Our state-of-the-art results validate the method qualitatively and for different metrics, for both geometric and color reconstruction.

Key facts. Cited by 126 papers in the map (data through 14 Oct 2026). Builds on 38 of its 48 references that are in the map. First posted on arXiv 19 Apr 2022.

Builds on

38 of 48 references.

References · 38

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2016Improved Techniques for Training GANscited by 2,970
  3. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
  4. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,200
  5. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,041
  6. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  7. 2019PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitizationcited by 818
  8. 2020Implicit Geometric Regularization for Learning Shapescited by 710
  9. 2020Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humanscited by 634
  10. 2020PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitizationcited by 521
  11. 2019PointRend: Image Segmentation as Renderingcited by 440
  12. 2019Making Convolutional Networks Shift-Invariant Againcited by 391
26 more
  1. 2020Implicit Functions in Feature Space for 3D Shape Reconstruction and Completioncited by 343
  2. 2020ARCH: Animatable Reconstruction of Clothed Humanscited by 257
  3. 2019Multi-Garment Net: Learning to Dress 3D People from Imagescited by 245
  4. 2018Video Based Reconstruction of 3D People Modelscited by 238
  5. 2020PaMIR: Parametric Model-Conditioned Implicit Representation for Image-based Human Reconstructioncited by 231
  6. 2017Photographic Image Synthesis with Cascaded Refinement Networkscited by 223
  7. 2019DeepHuman: 3D Human Reconstruction from a Single Imagecited by 182
  8. 2021ARCH++: Animation-Ready Clothed Human Reconstruction Revisitedcited by 174
  9. 2019Learning to Reconstruct People in Clothing from a Single RGB Cameracited by 168
  10. 2019Tex2Shape: Detailed Full Human Body Geometry From a Single Imagecited by 166
  11. 2021H-NeRF: Neural Radiance Fields for Rendering and Temporal Reconstruction of Humans in Motioncited by 157
  12. 2018BodyNet: Volumetric Inference of 3D Human Body Shapescited by 141
  13. 2017Deep Image Harmonizationcited by 120
  14. 2020Geo-PIFu: Geometry and Pixel Aligned Implicit Functions for Single-view Human Reconstructioncited by 112
  15. 2021LEAP: Learning Articulated Occupancy of Peoplecited by 107
  16. 2021Neural Actor: Neural Free-view Synthesis of Human Actors with Pose Controlcited by 106
  17. 2021imGHUM: Implicit Generative Models of 3D Human Shape and Articulated Posecited by 103
  18. 2021H3D-Net: Few-Shot High-Fidelity 3D Head Reconstructioncited by 81
  19. 2020Monocular Real-Time Volumetric Performance Capturecited by 74
  20. 2018SiCloPe: Silhouette-Based Clothed Peoplecited by 68
  21. 2019Moulding Humans: Non-parametric 3D Human Shape Estimation from Single Imagescited by 67
  22. 2021S3: Neural Shape, Skeleton, and Skinning Fields for 3D Human Modelingcited by 59
  23. 2019FACSIMILE: Fast and Accurate Scans From an Image in Less Than a Secondcited by 35
  24. 20183D Human Body Reconstruction from a Single Image via Volumetric Regressioncited by 29
  25. 2021Multi-person Implicit Reconstruction from a Single Imagecited by 13
  26. 2019Human Synthesis and Scene Compositingcited by 11

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 15; 2023: 44; 2024: 34; 2025: 26; 2026: 7.

126 papers.

Sort:

By area:

  1. 2024Sapiens: Foundation for Human Vision Modelscited by 229
  2. 2023GauHuman: Articulated Gaussian Splatting from Monocular Human Videoscited by 168
  3. 2022ARAH: Animatable Volume Rendering of Articulated Human SDFscited by 139
  4. 2023Vid2Avatar: 3D Avatar Reconstruction from Videos in the Wild via Self-supervised Scene Decompositioncited by 134
  5. 2023TeCH: Text-guided Reconstruction of Lifelike Clothed Humanscited by 104
  6. 2023SHERF: Generalizable Human NeRF from a Single Imagecited by 88
  7. 2022KeypointNeRF: Generalizing Image-based Volumetric Avatars using Relative Spatial Encoding of Keypointscited by 77
  8. 2023SIFU: Side-view Conditioned Implicit Function for Real-world Usable Clothed Human Reconstructioncited by 77
  9. 2023SiTH: Single-view Textured Human Reconstruction with Image-Conditioned Diffusioncited by 72
  10. 2023Learning Neural Volumetric Representations of Dynamic Humans in Minutescited by 70
  11. 2023High-fidelity 3D Human Digitization from Single 2K Resolution Imagescited by 70
  12. 2024Advances in 3D Generation: A Surveycited by 63
38 more
  1. 2023Learning Locally Editable Virtual Humanscited by 54
  2. 20244D-DRESS: A 4D Dataset of Real-world Human Clothing with Semantic Annotationscited by 54
  3. 2024HumanSplat: Generalizable Single-Image Human Gaussian Splatting with Structure Priorscited by 54
  4. 2024Human-3Diffusion: Realistic Avatar Creation via Explicit 3D Consistent Diffusion Modelscited by 44
  5. 20223D Clothed Human Reconstruction in the Wildcited by 42
  6. 2023Global-correlated 3D-decoupling Transformer for Clothed Avatar Reconstructioncited by 42
  7. 2023Single-Image 3D Human Digitization with Shape-Guided Diffusioncited by 42
  8. 2022One-shot Implicit Animatable Avatars with Model-based Priorscited by 38
  9. 2023High-Fidelity Clothed Avatar Reconstruction from a Single Imagecited by 38
  10. 2024AniGS: Animatable Gaussian Avatar from a Single Image with Inconsistent Gaussian Reconstructioncited by 36
  11. 2023SplatArmor: Articulated Gaussian splatting for animatable humans from monocular RGB videoscited by 35
  12. 2023Learning Clothing and Pose Invariant 3D Shape Representation for Long-Term Person Re-Identificationcited by 34
  13. 2022HumanGen: Generating Human Radiance Fields with Explicit Priorscited by 33
  14. 2024HAHA: Highly Articulated Gaussian Human Avatars with Textured Mesh Priorcited by 31
  15. 2025Vid2Avatar-Pro: Authentic Avatar from Videos in the Wild via Universal Priorcited by 31
  16. 2022State of the Art in Dense Monocular Non-Rigid 3D Reconstructioncited by 30
  17. 2023SMPLitex: A Generative Model and Dataset for 3D Human Texture Estimation from Single Imagecited by 30
  18. 2024Generalizable Human Gaussians from Single-View Imagecited by 29
  19. 2023DINAR: Diffusion Inpainting of Neural Textures for One-Shot Human Avatarscited by 28
  20. 2023Relightable and Animatable Neural Avatar from Sparse-View Videocited by 28
  21. 2022FOF: Learning Fourier Occupancy Field for Monocular Real-time Human Reconstructioncited by 27
  22. 2023D-IF: Uncertainty-aware Human Digitization via Implicit Distribution Fieldcited by 26
  23. 2023AI-Generated Content (AIGC) for Various Data Modalities: A Surveycited by 25
  24. 2022Self-Supervised Geometry-Aware Encoder for Style-Based 3D GAN Inversioncited by 24
  25. 2023Garment Recovery with Shape and Deformation Priorscited by 24
  26. 2023HumanRef: Single Image to 3D Human Generation via Reference-Guided Diffusioncited by 23
  27. 2024Morphable Diffusion: 3D-Consistent Diffusion for Single-image Avatar Creationcited by 23
  28. 2024PSHuman: Photorealistic Single-image 3D Human Reconstruction using Cross-Scale Multiview Diffusion and Explicit Remeshingcited by 23
  29. 2024GALA: Generating Animatable Layered Assets from a Single Scancited by 21
  30. 2023IntrinsicAvatar: Physically Based Inverse Rendering of Dynamic Humans from Monocular Videos via Explicit Ray Tracingcited by 20
  31. 2022Structured 3D Features for Reconstructing Controllable Avatarscited by 19
  32. 2024ReLoo: Reconstructing Humans Dressed in Loose Garments from Monocular Video in the Wildcited by 19
  33. 2024Disco4D: Disentangled 4D Human Generation and Animation from a Single Imagecited by 17
  34. 2023ConTex-Human: Free-View Rendering of Human from a Single Image with Texture-Consistent Synthesiscited by 16
  35. 2023SeSDF: Self-evolved Signed Distance Field for Implicit 3D Clothed Human Reconstructioncited by 15
  36. 2024Instant 3D Human Avatar Generation using Image Diffusion Modelscited by 14
  37. 2024DiffHuman: Probabilistic Photorealistic 3D Reconstruction of Humanscited by 13
  38. 2025PERSONA: Personalized Whole-Body 3D Avatar with Pose-Driven Deformations from a Single Imagecited by 13

50 most cited of 126 All 126 (JSON)