# Single-image Full-body Human Relighting

arXiv: https://arxiv.org/abs/2107.07259 · HTML: https://mlsanity.com/paper/2107.07259/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 59 references that are in the map.
- First posted on arXiv 15 Jul 2021.

## Builds on (most cited first, 18 of 18)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [NeRF++: Analyzing and Improving Neural Radiance Fields](https://mlsanity.com/paper/2010.07492/) (2020)
- [IBRNet: Learning Multi-View Image-Based Rendering](https://mlsanity.com/paper/2102.13090/) (2021)
- [NeRD: Neural Reflectance Decomposition from Image Collections](https://mlsanity.com/paper/2012.03918/) (2020)
- [Learning to Predict Indoor Illumination from a Single Image](https://mlsanity.com/paper/1704.00090/) (2017)
- [Single Image Portrait Relighting](https://mlsanity.com/paper/1905.00824/) (2019)
- [SfSNet: Learning Shape, Reflectance and Illuminance of Faces in the Wild](https://mlsanity.com/paper/1712.01261/) (2017)
- [Learning Physics-guided Face Relighting under Directional Light](https://mlsanity.com/paper/1906.03355/) (2019)
- [Learning Intrinsic Image Decomposition from Watching the World](https://mlsanity.com/paper/1804.00582/) (2018)
- [Neural Light Transport for Relighting and View Synthesis](https://mlsanity.com/paper/2008.03806/) (2020)
- [Deep Sky Modeling for Single Image Outdoor Lighting Estimation](https://mlsanity.com/paper/1905.03897/) (2019)
- [Deep Outdoor Illumination Estimation](https://mlsanity.com/paper/1611.06403/) (2016)
- [A Similarity Measure for Material Appearance](https://mlsanity.com/paper/1905.01562/) (2019)
- [The joint role of geometry and illumination on material recognition](https://mlsanity.com/paper/2101.02496/) (2021)
- [Intrinsic Light Field Images](https://mlsanity.com/paper/1608.04342/) (2016)

## Built on by (most cited first, 30 of 30)

- [DiLightNet: Fine-grained Lighting Control for Diffusion-based Image Generation](https://mlsanity.com/paper/2402.11929/) (2024)
- [Neural Gaffer: Relighting Any Object via Diffusion](https://mlsanity.com/paper/2406.07520/) (2024)
- [Learning to Relight Portrait Images via a Virtual Light Stage and Synthetic-to-Real Adaptation](https://mlsanity.com/paper/2209.10510/) (2022)
- [Relighting4D: Neural Relightable Human from Videos](https://mlsanity.com/paper/2207.07104/) (2022)
- [A Diffusion Approach to Radiance Field Relighting using Multi-Illumination Synthesis](https://mlsanity.com/paper/2409.08947/) (2024)
- [Geometry-aware Single-image Full-body Human Relighting](https://mlsanity.com/paper/2207.04750/) (2022)
- [MeshAvatar: Learning High-quality Triangular Human Avatars from Multi-view Videos](https://mlsanity.com/paper/2407.08414/) (2024)
- [De-rendering 3D Objects in the Wild](https://mlsanity.com/paper/2201.02279/) (2022)
- [OutCast: Outdoor Single-image Relighting with Cast Shadows](https://mlsanity.com/paper/2204.09341/) (2022)
- [RelightableHands: Efficient Neural Relighting of Articulated Hand Models](https://mlsanity.com/paper/2302.04866/) (2023)
- [Structured 3D Features for Reconstructing Controllable Avatars](https://mlsanity.com/paper/2212.06820/) (2022)
- [PRTGS: Precomputed Radiance Transfer of Gaussian Splats for Real-Time High-Quality Relighting](https://mlsanity.com/paper/2408.03538/) (2024)
- [URHand: Universal Relightable Hands](https://mlsanity.com/paper/2401.05334/) (2024)
- [RANA: Relightable Articulated Neural Avatars](https://mlsanity.com/paper/2212.03237/) (2022)
- [Comprehensive Relighting: Generalizable and Consistent Monocular Human Relighting and Harmonization](https://mlsanity.com/paper/2504.03011/) (2025)
- [Relightable Neural Human Assets from Multi-view Gradient Illuminations](https://mlsanity.com/paper/2212.07648/) (2022)
- [Learning Visibility Field for Detailed 3D Human Reconstruction and Relighting](https://mlsanity.com/paper/2304.11900/) (2023)
- [Generative Portrait Shadow Removal](https://mlsanity.com/paper/2410.05525/) (2024)
- [Makeup Extraction of 3D Representation via Illumination-Aware Image Decomposition](https://mlsanity.com/paper/2302.13279/) (2023)
- [Personalized Video Relighting With an At-Home Light Stage](https://mlsanity.com/paper/2311.08843/) (2023)
- [COMPOSE: Comprehensive Portrait Shadow Editing](https://mlsanity.com/paper/2408.13922/) (2024)
- [Deep Portrait Delighting](https://mlsanity.com/paper/2203.12088/) (2022)
- [Generalizable and Relightable Gaussian Splatting for Human Novel View Synthesis](https://mlsanity.com/paper/2505.21502/) (2025)
- [All-frequency Full-body Human Image Relighting](https://mlsanity.com/paper/2411.00356/) (2024)
- [SIDNet: Learning Shading-aware Illumination Descriptor for Image Harmonization](https://mlsanity.com/paper/2112.01314/) (2021)
- [FashionR2R: Texture-preserving Rendered-to-Real Image Translation with Diffusion Models](https://mlsanity.com/paper/2410.14429/) (2024)
- [Single-image Reflectance and Transmittance Estimation from Any Flatbed Scanner](https://mlsanity.com/paper/2502.14462/) (2025)
- [HumanMaterial: Human Material Estimation from a Single Image via Progressive Training](https://mlsanity.com/paper/2507.18385/) (2025)
- [HAFMat: Hybrid Priors Guided Adaptive Fusion for Single-Image Human Material Estimation](https://mlsanity.com/paper/2606.16323/) (2026)
- [RelightFormer: Feed-forward Generative Transformer for Multiview Object Relighting](https://mlsanity.com/paper/2609.07414/) (2026)

## 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.