SunStage: Portrait Reconstruction and Relighting Using the Sun as a Light Stage
Yifan Wang, Aleksander Holynski, Xiuming Zhang, Xuaner Zhang
Abstract
sunstage.cs.washington.edu (a) Reconstruction (b) Edit lighting (c) Soften shadows (d) Swap lighting (e) Edit texture Figure 1. Given a selfie video rotating under the sun, SunStage reconstructs geometry, material, camera pose, and lighting information. This recovered information can be used to (a) realistically re-render the input images, (b) modify the lighting conditions by adding / removing lights, (c) soften harsh shadows by changing the size of the reconstructed light sources (d) render the person in an entirely new environment, and (e) edit the albedo or material properties to add freckles, makeup, or stickers that realistically interact with scene lighting.
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.
Cited by top-tier papers22
- TC-Light: Temporally Coherent Generative Rendering for Realistic World TransferYang Liu, Chuanchen Luo, Zimo Tang, Yingyan Li et al.NeurIPS 2025 · 12 citations
- Holo-Relighting: Controllable Volumetric Portrait Relighting from a Single ImageYiqun Mei, Yu Zeng, He Zhang, Zhixin Shu et al.CVPR 2024 · 11 citations
- Text2Relight: Creative Portrait Relighting with Text GuidanceJunuk Cha, Mengwei Ren, Krishna Kumar Singh, He Zhang et al.AAAI 2025 · 9 citations
- IllumiCraft: Unified Geometry and Illumination Diffusion for Controllable Video GenerationYuanze Lin, Yi-Wen Chen, Yi-Hsuan Tsai, Ronald Clark et al.NeurIPS 2025 · 6 citations
- Light-a-Video: Training-Free Video Relighting via Progressive Light FusionYujie Zhou, Jiazi Bu, Pengyang Ling, Pan Zhang et al.ICCV 2025 · 4 citations
Builds on12
- Learning an animatable detailed 3D face model from in-the-wild imagesYao Feng, Haiwen Feng, Michael J. Black, Timo BolkartSIGGRAPH 2021 · 662 citations
- Deep Single-Image Portrait RelightingHao Zhou, Sunil Hadap, Kalyan Sunkavalli, David JacobsICCV 2019 · 247 citations
- Total relighting: learning to relight portraits for background replacementRohit Pandey, Sergio Orts-Escolano, Chloe LeGendre, Christian Häne et al.SIGGRAPH 2021 · 138 citations
- Portrait shadow manipulationXuaner Cecilia Zhang, Jonathan T. Barron, Yun-Ta Tsai, Rohit Pandey et al.SIGGRAPH 2020 · 104 citations
- Deep relightable appearance models for animatable facesSai Bi, Stephen Lombardi, Shunsuke Saito, Tomas Simon et al.SIGGRAPH 2021 · 75 citations
Related papers
- GroomLight: Hybrid Inverse Rendering for Relightable Human Hair Appearance ModelingYang Zheng, Menglei Chai, Delio Vicini, Yuxiao Zhou et al.CVPR 2025
- Relightable Neural Human Assets from Multi-view Gradient IlluminationsTaotao Zhou, Kai He, Di Wu, Teng Xu et al.CVPR 2023
- A Light Stage on Every DeskSoumyadip Sengupta, Brian Curless, Ira Kemelmacher-Shlizerman, Steven M. SeitzICCV 2021 · 32 citations
- HRAvatar: High-Quality and Relightable Gaussian Head AvatarDongbin Zhang, Yunfei Liu, Lijian Lin, Ye Zhu et al.CVPR 2025
- Shape and Material Capture at HomeDaniel Lichy, Jiaye Wu, Soumyadip Sengupta, David W. JacobsCVPR 2021
