Overview

3D face reconstruction estimates a person's facial shape, appearance, and often expression or motion from photos, video, or sparse multi-view captures, enabling avatars, performance capture, editing, and analysis. Methods range from 3D morphable models fitted with landmarks and inverse rendering to neural fields and 3D Gaussian splats, with canonical meshes, learned priors, and diffusion used to infer unseen views and fine detail. Current work targets fast few-shot reconstruction, animation and relighting, and consistent meshes, while addressing hair, occlusion, profiles, and changing expressions. A central challenge is balancing identity-faithful geometry and cross-view consistency with photorealism, speed, and generalization from limited input, while ensuring evaluations reflect perceptually important detail and potential bias.

Latest papers

CardsList

58 papers3 papers in the last four weeks, level with the four weeks before. 0.0% of all new papers.

  1. ViGA-FLAME: Aligning Latent Visual and Geometric Representations for Robust 3D Head Expression Estimation

    Nov 10, 2026Wen Hao He, Jiacheng Wu, Jie Chen3D Face ReconstructionGeometric Representation Learning

  2. Joint Rigid Alignment and Morphable Reconstruction from Partial 3D Face Scans

    Oct 29, 2026Eli A. Underwood, Nicolas Rondan, Angel V. Peterchev +13D Face ReconstructionPoint Cloud Registration

  3. Vision Tomography: Towards Portable 3D Bidirectional Face-Skull Inference from Visual Data

    Oct 27, 2026Zidu Wang, Meng Xu, Miao Xu +53D Morphable Models3D Face Reconstruction

  4. EGGHead: Efficient Generalizable Gaussian Heads from a Single Image

    Oct 16, 2026Pilseo Park, Andrew Hou, Michel Sarkis +33D Face ReconstructionSingle-View 3D Reconstruction

  5. Fresco++: Frequency-Guided and Canonical-Consistent Optimization for Fine-Grained Head Avatar Modeling

    Oct 8, 2026Shikun Zhang, Yong Li, Yiqun Wang +13D Avatar Generation3D Face Reconstruction

  6. Relightable 3D Avatar Reconstruction with Semantic-Adaptive Motion-Illumination Responses

    Sep 21, 2026Jiankuo Zhao, Xiangyu Zhu, Jijie Li +33D Gaussian Splatting3D Avatar Generation

  7. MGAvatar: Mesh-Bound Gaussians for Head Avatar Geometry and Appearance Modeling

    Sep 11, 2026Lei Shi, Sen Peng, Zhiyang Deng +43D Gaussian Splatting3D Avatar Generation

  8. FaceSnap: Real-Time Personalized Lightstage Facial Performance Capture

    Aug 31, 2026Rukhshanda Hussain, Noé Artru, Emeline Got +64D Reconstruction3D Face Reconstruction

  9. RealDenseFace: Real-time Monocular 3D Face Reconstruction from Dense UV-space Priors

    Aug 10, 2026Linzhou Li, Tianjia Shao, Kun ZhouStreaming 3D Reconstruction3D Morphable Models

  10. GNM Head: A Generative aNthropometric Model of the human head

    Jul 26, 2026Stylianos Ploumpis, Jan Bednarik, Gaspard Zoss +293D Morphable Models3D Face Reconstruction

  11. GRAPE: Graduated Routing for Articulated Portrait mesh Estimation

    Jul 26, 2026Yunfei Liu, Lijian Lin, Ye Zhu +13D Morphable Models3D Reconstruction

  12. fMRI2Face: A Full-HD fMRI-Video Dataset and Geometry-Guided Neural Decoding Framework for Dynamic Human Face Reconstruction

    Jul 24, 2026Jingyang Huo, Xiangru Huang, Chentao Shen +6Video Diffusion ModelsNeural Decoding

  13. FA-LAM: Focus-Aware Large Avatar Model for One-Shot 4D Animatable Gaussian Head

    Jul 23, 2026Yingdong Hu, Yisheng He, Yiming Jiang +33D Gaussian Splatting4D Reconstruction

  14. UVFaceFusion: Fast Multi-view Topologically Consistent Face Reconstruction in the Wild via UV-space Neural Fusion

    Jul 21, 2026Xin Ming, Yuxuan Han, Junhai Yong +13D ReconstructionMulti-View 3D Reconstruction

  15. Discovering Geometric Biases in 3D Face Reconstruction: A Curvature-Aware Spectral Framework for Fairness Evaluation

    Jul 8, 2026Veronika Shilova, Emmanuel Malherbe, Giovanni Palma +33D Morphable Models3D Face Reconstruction

  16. FFAvatar: Feed-Forward 4D Head Avatar Reconstruction from Sparse Portrait Images

    Jun 29, 2026Jianjiang Yao, Ke Xian, Renxiang Dai +1Feed-Forward 3D Reconstruction4D Reconstruction

  17. FiCA: Feed-forward instant Gaussian Codec Avatars from a Single Portrait Image

    Jun 23, 2026Kim Youwang, Zhengyu Yang, Liuhao Ge +83D Asset Generation3D Reconstruction

  18. ReAge3D: Re-Aging 3D Faces with View Consistency

    Jun 16, 2026Libing Zeng, Li Ma, Mingming He +33D Face ReconstructionDiffusion-Based Image Editing

  19. SpatialAvatar-0: High-Quality 4D Head Avatar with Multi-Stage Reconstruction

    Jun 14, 2026Yiran Wang, Zeyu Zhang, Yuanming Li +23D Gaussian Splatting4D Reconstruction

  20. Wispy to Voluminous: Prior-free Multi-view Capture of Strand-level Facial Hair

    Jun 6, 2026Jaeseong Lee, Giljoo Nam, Adrian Jarabo +13D ReconstructionMulti-View 3D Reconstruction

  21. Self-Learning Expression Deformations for Data-Efficient Gaussian Avatars

    Jun 4, 2026Jiahao Yang, Xiaohang Yang, Qing Wang +33D Gaussian SplattingSelf-Supervised Learning

  22. Splatshot: 3D Face Avatar Generation from a Single Unconstrained Photo

    May 31, 2026Hao Liang, Zhixuan Ge, Soumendu Majee +33D Gaussian Splatting3D Asset Generation

  23. SplitAvatar: One-shot Head Avatar with Autoregressive Gaussian Splitting

    May 25, 2026Hongzhe Liao, Chuhua Xian, Hongmin Cai +23D Gaussian SplattingAdaptive Gaussian Densification

  24. FFAvatar: Few-Shot, Feed-Forward, and Generalizable Avatar Reconstruction

    May 14, 2026Thuan Hoang Nguyen, Jiahao Luo, Yinyu Nie +33D Gaussian Splatting3D Reconstruction