# Deep Portrait Lighting Enhancement with 3D Guidance

arXiv: https://arxiv.org/abs/2108.02121 · HTML: https://mlsanity.com/paper/2108.02121/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 48 references that are in the map.
- First posted on arXiv 4 Aug 2021.

## Builds on (most cited first, 30 of 34)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Semantic Image Synthesis with Spatially-Adaptive Normalization](https://mlsanity.com/paper/1903.07291/) (2019)
- [High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs](https://mlsanity.com/paper/1711.11585/) (2017)
- [Deep Retinex Decomposition for Low-Light Enhancement](https://mlsanity.com/paper/1808.04560/) (2018)
- [Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement](https://mlsanity.com/paper/2001.06826/) (2020)
- [Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Set](https://mlsanity.com/paper/1903.08527/) (2019)
- [EnlightenGAN: Deep Light Enhancement without Paired Supervision](https://mlsanity.com/paper/1906.06972/) (2019)
- [Neural 3D Mesh Renderer](https://mlsanity.com/paper/1711.07566/) (2017)
- [Soft Rasterizer: A Differentiable Renderer for Image-based 3D Reasoning](https://mlsanity.com/paper/1904.01786/) (2019)
- [Learning to Estimate 3D Human Pose and Shape from a Single Color Image](https://mlsanity.com/paper/1805.04092/) (2018)
- [Learning to Predict 3D Objects with an Interpolation-based Differentiable Renderer](https://mlsanity.com/paper/1908.01210/) (2019)
- [Multi-view Supervision for Single-view Reconstruction via Differentiable Ray Consistency](https://mlsanity.com/paper/1704.06254/) (2017)
- [Single Image Portrait Relighting](https://mlsanity.com/paper/1905.00824/) (2019)
- [High-Fidelity Pluralistic Image Completion with Transformers](https://mlsanity.com/paper/2103.14031/) (2021)
- [SfSNet: Learning Shape, Reflectance and Illuminance of Faces in the Wild](https://mlsanity.com/paper/1712.01261/) (2017)
- [Perspective Transformer Nets: Learning Single-View 3D Object Reconstruction without 3D Supervision](https://mlsanity.com/paper/1612.00814/) (2016)
- [Learning Physics-guided Face Relighting under Directional Light](https://mlsanity.com/paper/1906.03355/) (2019)
- [Neural Face Editing with Intrinsic Image Disentangling](https://mlsanity.com/paper/1704.04131/) (2017)
- [World-Consistent Video-to-Video Synthesis](https://mlsanity.com/paper/2007.08509/) (2020)
- [Residual Conv-Deconv Grid Network for Semantic Segmentation](https://mlsanity.com/paper/1707.07958/) (2017)
- [Foreground-aware Semantic Representations for Image Harmonization](https://mlsanity.com/paper/2006.00809/) (2020)
- [A Dataset of Multi-Illumination Images in the Wild](https://mlsanity.com/paper/1910.08131/) (2019)
- [A Versatile Scene Model with Differentiable Visibility Applied to Generative Pose Estimation](https://mlsanity.com/paper/1602.03725/) (2016)
- [Portrait Shadow Manipulation](https://mlsanity.com/paper/2005.08925/) (2020)
- [Towards High Fidelity Face Relighting with Realistic Shadows](https://mlsanity.com/paper/2104.00825/) (2021)

## Built on by (most cited first, 2 of 2)

- [SunStage: Portrait Reconstruction and Relighting using the Sun as a Light Stage](https://mlsanity.com/paper/2204.03648/) (2022)
- [Generative Portrait Shadow Removal](https://mlsanity.com/paper/2410.05525/) (2024)

## Abstract (arXiv)

Despite recent breakthroughs in deep learning methods for image lighting enhancement, they are inferior when applied to portraits because 3D facial information is ignored in their models. To address this, we present a novel deep learning framework for portrait lighting enhancement based on 3D facial guidance. Our framework consists of two stages. In the first stage, corrected lighting parameters are predicted by a network from the input bad lighting image, with the assistance of a 3D morphable model and a differentiable renderer. Given the predicted lighting parameter, the differentiable renderer renders a face image with corrected shading and texture, which serves as the 3D guidance for learning image lighting enhancement in the second stage. To better exploit the long-range correlations between the input and the guidance, in the second stage, we design an image-to-image translation network with a novel transformer architecture, which automatically produces a lighting-enhanced result. Experimental results on the FFHQ dataset and in-the-wild images show that the proposed method outperforms state-of-the-art methods in terms of both quantitative metrics and visual quality. We will publish our dataset along with more results on https://cassiepython.github.io/egsr/index.html.