mlsanityData to 7 Oct 2026

Single-image Full-body Human Relighting

arXiv 2107.07259 ↗First posted 15 Jul 2021cs.CV cs.GRcited by 30

Not on the map. Why?

Abstract (arXiv)

We present a single-image data-driven method to automatically relight images with full-body humans in them. Our framework is based on a realistic scene decomposition leveraging precomputed radiance transfer (PRT) and spherical harmonics (SH) lighting. In contrast to previous work, we lift the assumptions on Lambertian materials and explicitly model diffuse and specular reflectance in our data. Moreover, we introduce an additional light-dependent residual term that accounts for errors in the PRT-based image reconstruction. We propose a new deep learning architecture, tailored to the decomposition performed in PRT, that is trained using a combination of L1, logarithmic, and rendering losses. Our model outperforms the state of the art for full-body human relighting both with synthetic images and photographs.

Key facts. Cited by 30 papers in the map (data through 7 Oct 2026). Builds on 18 of its 59 references that are in the map. First posted on arXiv 15 Jul 2021.

Builds on

18 of 59 references.

References · 18

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  5. 2020NeRF++: Analyzing and Improving Neural Radiance Fieldscited by 857
  6. 2021IBRNet: Learning Multi-View Image-Based Renderingcited by 698
  7. 2020NeRD: Neural Reflectance Decomposition from Image Collectionscited by 446
  8. 2017Learning to Predict Indoor Illumination from a Single Imagecited by 160
  9. 2019Single Image Portrait Relightingcited by 152
  10. 2017SfSNet: Learning Shape, Reflectance and Illuminance of Faces in the Wildcited by 110
  11. 2019Learning Physics-guided Face Relighting under Directional Lightcited by 90
  12. 2018Learning Intrinsic Image Decomposition from Watching the Worldcited by 74
6 more
  1. 2020Neural Light Transport for Relighting and View Synthesiscited by 73
  2. 2019Deep Sky Modeling for Single Image Outdoor Lighting Estimationcited by 66
  3. 2016Deep Outdoor Illumination Estimationcited by 53
  4. 2019A Similarity Measure for Material Appearancecited by 19
  5. 2021The joint role of geometry and illumination on material recognitioncited by 5
  6. 2016Intrinsic Light Field Imagescited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 9; 2023: 4; 2024: 10; 2025: 4; 2026: 2.

30 papers.

Sort:

By area:

  1. 2024DiLightNet: Fine-grained Lighting Control for Diffusion-based Image Generationcited by 93
  2. 2024Neural Gaffer: Relighting Any Object via Diffusioncited by 91
  3. 2022Learning to Relight Portrait Images via a Virtual Light Stage and Synthetic-to-Real Adaptationcited by 67
  4. 2022Relighting4D: Neural Relightable Human from Videoscited by 41
  5. 2024A Diffusion Approach to Radiance Field Relighting using Multi-Illumination Synthesiscited by 37
  6. 2022Geometry-aware Single-image Full-body Human Relightingcited by 34
  7. 2024MeshAvatar: Learning High-quality Triangular Human Avatars from Multi-view Videoscited by 34
  8. 2022De-rendering 3D Objects in the Wildcited by 31
  9. 2022OutCast: Outdoor Single-image Relighting with Cast Shadowscited by 30
  10. 2023RelightableHands: Efficient Neural Relighting of Articulated Hand Modelscited by 21
  11. 2022Structured 3D Features for Reconstructing Controllable Avatarscited by 19
  12. 2024URHand: Universal Relightable Handscited by 17
18 more
  1. 2024PRTGS: Precomputed Radiance Transfer of Gaussian Splats for Real-Time High-Quality Relightingcited by 17
  2. 2022RANA: Relightable Articulated Neural Avatarscited by 12
  3. 2025Comprehensive Relighting: Generalizable and Consistent Monocular Human Relighting and Harmonizationcited by 12
  4. 2022Relightable Neural Human Assets from Multi-view Gradient Illuminationscited by 11
  5. 2023Learning Visibility Field for Detailed 3D Human Reconstruction and Relightingcited by 11
  6. 2024Generative Portrait Shadow Removalcited by 10
  7. 2023Makeup Extraction of 3D Representation via Illumination-Aware Image Decompositioncited by 8
  8. 2023Personalized Video Relighting With an At-Home Light Stagecited by 7
  9. 2024COMPOSE: Comprehensive Portrait Shadow Editingcited by 6
  10. 2022Deep Portrait Delightingcited by 4
  11. 2025Generalizable and Relightable Gaussian Splatting for Human Novel View Synthesiscited by 4
  12. 2024All-frequency Full-body Human Image Relightingcited by 3
  13. 2021SIDNet: Learning Shading-aware Illumination Descriptor for Image Harmonizationcited by 2
  14. 2024FashionR2R: Texture-preserving Rendered-to-Real Image Translation with Diffusion Modelscited by 1
  15. 2025Single-image Reflectance and Transmittance Estimation from Any Flatbed Scannercited by 1
  16. 2025HumanMaterial: Human Material Estimation from a Single Image via Progressive Trainingcited by 1
  17. 2026HAFMat: Hybrid Priors Guided Adaptive Fusion for Single-Image Human Material Estimationcited by 0
  18. 2026RelightFormer: Feed-forward Generative Transformer for Multiview Object Relightingcited by 0