High-Quality Facial Geometry and Appearance Capture at Home
Yuxuan Han, Junfeng Lyu, Feng Xu
Abstract
Data Capture Recon. Geometry and Reflectance a single co-located sequence normal mesh diffuse albedo specular albedo roughness Relighting high-quality renderings with plausible eyes' specularities Figure 1. We propose a novel method for high-quality face capture, featuring a low-cost and easy-to-use capture setup and the capability to model the complete face with skin, mouth interior, hair, and eyes. Our method takes a single co-located smartphone flashlight sequence captured in a dim room (e.g. rooms with curtains or at night) as input. It reconstructs relightable 3D face assets from the recorded data. These can be used by common graphics software like Blender to create photo-realistic renderings in new environments.
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 3ab4aa98-a5da-435a-89d7-15893c45f4b2Cited by top-tier papers6
- Facial Appearance Capture at Home with Patch-Level Reflectance PriorYuxuan Han, Junfeng Lyu, Kuan Sheng, Minghao Que et al.SIGGRAPH 2025 · 2 citations
- VGGTFace: Topologically Consistent Facial Geometry Reconstruction in the WildXin Ming, Yuxuan Han, Tianyu Huang, Feng XuAAAI 2026 · 2 citations
- WildCap: Facial Albedo Capture in the Wild via Hybrid Inverse RenderingYuxuan Han, Xin Ming, Tianxiao Li, Zhuofan Shen et al.CVPR 2026 · 1 citation
- Monocular Facial Appearance Capture in the WildYingyan Xu, Kate Gadola, Prashanth Chandran, Sebastian Weiss et al.ICCV 2025
- RelightAnyone: A Generalized Relightable 3D Gaussian Head ModelYingyan Xu, Pramod Rao, Sebastian Weiss, Gaspard Zoss et al.CVPR 2026
Builds on31
- Instant neural graphics primitives with a multiresolution hash encodingThomas Müller, Alex Evans, Christoph Schied, Alexander KellerSIGGRAPH 2022 · 4,089 citations
- Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance FieldsJonathan T. Barron, Ben Mildenhall, Matthew Tancik, Peter Hedman et al.ICCV 2021 · 2,700 citations
- NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view ReconstructionPeng Wang, Lingjie Liu, Yuan Liu, Christian Theobalt et al.NeurIPS 2021 · 2,500 citations
- Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance FieldsJonathan T. Barron, Ben Mildenhall, Dor Verbin, Pratul P. Srinivasan et al.CVPR 2022 · 1,603 citations
- Volume Rendering of Neural Implicit SurfacesLior Yariv, Jiatao Gu, Yoni Kasten, Yaron LipmanNeurIPS 2021 · 1,421 citations
Related papers
- Single-shot high-quality facial geometry and skin appearance captureJérémy Riviere, Paulo F. U. Gotardo, Derek Bradley, Abhijeet Ghosh et al.SIGGRAPH 2020 · 66 citations
- EyeNeRF: a hybrid representation for photorealistic synthesis, animation and relighting of human eyesGengyan Li, Abhimitra Meka, Franziska Mueller, Marcel C. Bühler et al.SIGGRAPH 2022 · 39 citations
- Shape and Material Capture at HomeDaniel Lichy, Jiaye Wu, Soumyadip Sengupta, David W. JacobsCVPR 2021
- Deep relightable appearance models for animatable facesSai Bi, Stephen Lombardi, Shunsuke Saito, Tomas Simon et al.SIGGRAPH 2021 · 75 citations
- High-Fidelity Face Tracking for AR/VR via Deep Lighting AdaptationLele Chen, Chen Cao, Fernando De la Torre, Jason M. Saragih et al.CVPR 2021
