SynthLight: Portrait Relighting with Diffusion Model by Learning to Re-render Synthetic Faces
Sumit Chaturvedi, Mengwei Ren, Yannick Hold-Geoffroy, Jingyuan Liu, Julie Dorsey, Zhixin Shu
Abstract
Figure 1. SynthLight performs relighting on portraits using an environment map lighting. By learning to re-render synthetic human faces, our diffusion model produces realistic illumination effects on real portrait photographs, including distinct cast shadows on the neck and natural specular highlights on the skin. Despite being trained exclusively on synthetic headshot images for relighting, the model demonstrates remarkable generalization to diverse scenarios, successfully handling half-body portraits and even full-body figurines.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext 5562ee6a-34e4-4bb7-8a14-a7c78c8672deCited by top-tier papers16
- Light-X: Generative 4D Video Rendering with Camera and Illumination ControlTianqi Liu, Zhaoxi Chen, Zihao Huang, Shaocong Xu et al.ICLR 2026 · 12 citations
- UniLumos: Fast and Unified Image and Video Relighting with Physics-Plausible FeedbackPengwei Liu, Hangjie Yuan, Bo Dong, Jiazheng Xing et al.NeurIPS 2025 · 10 citations
- LuxRemix: Lighting Decomposition and Remixing for Indoor ScenesRuofan Liang, Norman Müller, Ethan Weber, Duncan Zauss et al.CVPR 2026 · 7 citations
- FaceLift: Learning Generalizable Single Image 3D Face Reconstruction From Synthetic HeadsWeijie Lyu, Yi Zhou, Ming-Hsuan Yang, Zhixin ShuICCV 2025 · 5 citations
- GeoRelight: Learning Joint Geometrical Relighting and Reconstruction with Flexible Multi-Modal Diffusion TransformersYuxuan Xue, Ruofan Liang, Egor Zakharov, Timur M. Bagautdinov et al.CVPR 2026 · 4 citations
Builds on30
- Denoising Diffusion Probabilistic ModelsJonathan Ho, Ajay Jain, Pieter AbbeelNeurIPS 2020 · 35,902 citations
- LoRA: Low-Rank Adaptation of Large Language ModelsEdward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu et al.ICLR 2022 · 18,833 citations
- High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser et al.CVPR 2022 · 13,123 citations
- Directly Denoising Diffusion ModelsDan Zhang, Jingjing Wang, Feng LuoICML 2024 · 11,724 citations
- Visual Instruction TuningHaotian Liu, Chunyuan Li, Qingyang Wu, Yong Jae LeeNeurIPS 2023 · 11,349 citations
Related papers
- Pixel Cube: Diffusion-based Portrait Video Relighting Through Realistic Lighting ReproductionYufan Zhang, Yu Ji, Ayo Ajiboye, Rundi Wu et al.SIGGRAPH 2026
- Relightful Harmonization: Lighting-Aware Portrait Background ReplacementMengwei Ren, Wei Xiong, Jae Shin Yoon, Zhixin Shu et al.CVPR 2024 · 17 citations
- Total relighting: learning to relight portraits for background replacementRohit Pandey, Sergio Orts-Escolano, Chloe LeGendre, Christian Häne et al.SIGGRAPH 2021 · 138 citations
- Controllable Light Diffusion for PortraitsDavid Futschik, Kelvin Ritland, James Vecore, Sean Fanello et al.CVPR 2023
- GroomLight: Hybrid Inverse Rendering for Relightable Human Hair Appearance ModelingYang Zheng, Menglei Chai, Delio Vicini, Yuxiao Zhou et al.CVPR 2025
