High-Fidelity Face Tracking for AR/VR via Deep Lighting Adaptation
Lele Chen, Chen Cao, Fernando De la Torre, Jason M. Saragih, Chenliang Xu, Yaser Sheikh
2021Year
6Top-tier citations
Abstract
Relit avatar under different viewpoints Relit avatar Normal map Fully-lit avatar Figure 1. High-fidelity face tracking results using our method. From left to right: Input image captured by iPhone, normal map, fully-lit avatar (avatar before relighting), relit avatar (avatar after relighting), and relit avatar under different viewpoints. Please notice the specular highlight changes on the avatars under different viewpoints.
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 4a6ea3e8-9972-424f-9d55-afdb5debbf59Cited by top-tier papers6
- Expressive Talking Head Generation with Granular Audio-Visual ControlBorong Liang, Yan Pan, Zhizhi Guo, Hang Zhou et al.CVPR 2022 · 114 citations
- Emotional Listener Portrait: Realistic Listener Motion Simulation in ConversationLuchuan Song, Guojun Yin, Zhenchao Jin, Xiaoyi Dong et al.ICCV 2023 · 19 citations
- Robust Egocentric Photo-realistic Facial Expression Transfer for Virtual RealityAmin Jourabloo, Fernando De la Torre, Jason M. Saragih, Shih-En Wei et al.CVPR 2022 · 13 citations
- ELITE: Efficient Gaussian Head Avatar from a Monocular Video via Learned Initialization and Test-time Generative AdaptationKim Youwang, Lee Hyoseok, Subin Park, Gerard Pons-Moll et al.CVPR 2026 · 1 citation
- LLM-driven Multimodal and Multi-Identity Listening Head GenerationPeiwen Lai, Weizhi Zhong, Yipeng Qin, Xiaohang Ren et al.CVPR 2025
Builds on8
- Few-Shot Adversarial Learning of Realistic Neural Talking Head ModelsEgor Zakharov, Aliaksandra Shysheya, Egor Burkov, Victor S. LempitskyICCV 2019 · 687 citations
- Towards High-Fidelity 3D Face Reconstruction From In-the-Wild Images Using Graph Convolutional NetworksJiangke Lin, Yi Yuan, Tianjia Shao, Kun ZhouCVPR 2020
- Lightweight Photometric Stereo for Facial Details RecoveryXueying Wang, Yudong Guo, Bailin Deng, Juyong ZhangCVPR 2020
- Rotate-and-Render: Unsupervised Photorealistic Face Rotation From Single-View ImagesHang Zhou, Jihao Liu, Ziwei Liu, Yu Liu et al.CVPR 2020
- Learning Physics-Guided Face Relighting Under Directional LightThomas Nestmeyer, Jean-François Lalonde, Iain A. Matthews, Andreas M. LehrmannCVPR 2020
Related papers
- Relightable and Animatable Neural Avatar from Sparse-View VideoZhen Xu, Sida Peng, Chen Geng, Linzhan Mou et al.CVPR 2024
- FitMe: Deep Photorealistic 3D Morphable Model AvatarsAlexandros Lattas, Stylianos Moschoglou, Stylianos Ploumpis, Baris Gecer et al.CVPR 2023
- Relightable Full-Body Gaussian Codec AvatarsShaofei Wang, Tomas Simon, Igor Santesteban, Timur M. Bagautdinov et al.SIGGRAPH 2025 · 6 citations
- SynthLight: Portrait Relighting with Diffusion Model by Learning to Re-render Synthetic FacesSumit Chaturvedi, Mengwei Ren, Yannick Hold-Geoffroy, Jingyuan Liu et al.CVPR 2025
- GroomLight: Hybrid Inverse Rendering for Relightable Human Hair Appearance ModelingYang Zheng, Menglei Chai, Delio Vicini, Yuxiao Zhou et al.CVPR 2025
