FaceVerse: a Fine-grained and Detail-controllable 3D Face Morphable Model from a Hybrid Dataset
Not on the map. Why?
Abstract (arXiv)
We present FaceVerse, a fine-grained 3D Neural Face Model, which is built from hybrid East Asian face datasets containing 60K fused RGB-D images and 2K high-fidelity 3D head scan models. A novel coarse-to-fine structure is proposed to take better advantage of our hybrid dataset. In the coarse module, we generate a base parametric model from large-scale RGB-D images, which is able to predict accurate rough 3D face models in different genders, ages, etc. Then in the fine module, a conditional StyleGAN architecture trained with high-fidelity scan models is introduced to enrich elaborate facial geometric and texture details. Note that different from previous methods, our base and detailed modules are both changeable, which enables an innovative application of adjusting both the basic attributes and the facial details of 3D face models. Furthermore, we propose a single-image fitting framework based on differentiable rendering. Rich experiments show that our method outperforms the state-of-the-art methods.
Key facts. Cited by 98 papers in the map (data through 7 Oct 2026). Builds on 26 of its 48 references that are in the map. First posted on arXiv 26 Mar 2022.
Builds on
26 of 48 references.
References · 26
- 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
- 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
- 2020Face2Face: Real-time Face Capture and Reenactment of RGB Videoscited by 631
- 2019Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Setcited by 481
- 2020Learning an Animatable Detailed 3D Face Model from In-The-Wild Imagescited by 475
- 2021Function4D: Real-time Human Volumetric Capture from Very Sparse Consumer RGBD Sensorscited by 246
- 2020Towards Fast, Accurate and Stable 3D Dense Face Alignmentcited by 219
- 2020FaceScape: a Large-scale High Quality 3D Face Dataset and Detailed Riggable 3D Face Predictioncited by 196
- 2018Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Networkcited by 195
- 2015DeepStereo: Learning to Predict New Views from the World's Imagerycited by 185
- 2017MoFA: Model-based Deep Convolutional Face Autoencoder for Unsupervised Monocular Reconstructioncited by 163
- 2018Nonlinear 3D Face Morphable Modelcited by 157
14 more
- 2016Regressing Robust and Discriminative 3D Morphable Models with a very Deep Neural Networkcited by 109
- 2020Learning Formation of Physically-Based Face Attributescited by 94
- 2017Self-supervised Multi-level Face Model Learning for Monocular Reconstruction at over 250 Hzcited by 91
- 2019Towards High-fidelity Nonlinear 3D Face Morphable Modelcited by 91
- 2016Learning Detailed Face Reconstruction from a Single Imagecited by 71
- 2021DeepMultiCap: Performance Capture of Multiple Characters Using Sparse Multiview Camerascited by 67
- 2017Unrestricted Facial Geometry Reconstruction Using Image-to-Image Translationcited by 56
- 2019Disentangled Representation Learning for 3D Face Shapecited by 48
- 2017End-to-end 3D face reconstruction with deep neural networkscited by 47
- 2020High-Fidelity 3D Digital Human Head Creation from RGB-D Selfiescited by 47
- 2019Photo-Realistic Facial Details Synthesis from Single Imagecited by 40
- 2014Multilinear Wavelets: A Statistical Shape Space for Human Facescited by 32
- 2019Self-supervised Learning of Detailed 3D Face Reconstructioncited by 21
- 2018View Extrapolation of Human Body from a Single Imagecited by 11
Built on by
Citing papers per year: 2022: 13; 2023: 28; 2024: 16; 2025: 27; 2026: 14.
98 papers.
Sort:
By area:
- 2023Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priorscited by 395
- 2022PyMAF-X: Towards Well-aligned Full-body Model Regression from Monocular Imagescited by 152
- 2022Next3D: Generative Neural Texture Rasterization for 3D-Aware Head Avatarscited by 124
- 2023MonoGaussianAvatar: Monocular Gaussian Point-based Head Avatarcited by 89
- 2023AvatarReX: Real-time Expressive Full-body Avatarscited by 83
- 2022KeypointNeRF: Generalizing Image-based Volumetric Avatars using Relative Spatial Encoding of Keypointscited by 77
- 2023DiffusionRig: Learning Personalized Priors for Facial Appearance Editingcited by 74
- 2022AvatarMAV: Fast 3D Head Avatar Reconstruction Using Motion-Aware Neural Voxelscited by 73
- 2022Learning Neural Parametric Head Modelscited by 73
- 2022ClipFace: Text-guided Editing of Textured 3D Morphable Modelscited by 59
- 2023StyleAvatar: Real-time Photo-realistic Portrait Avatar from a Single Videocited by 52
- 2022Visual Speech-Aware Perceptual 3D Facial Expression Reconstruction from Videoscited by 50
38 more
- 2023VividTalk: One-Shot Audio-Driven Talking Head Generation Based on 3D Hybrid Priorcited by 47
- 2024NPGA: Neural Parametric Gaussian Avatarscited by 46
- 2023DiffusionAvatars: Deferred Diffusion for High-fidelity 3D Head Avatarscited by 42
- 2022FFHQ-UV: Normalized Facial UV-Texture Dataset for 3D Face Reconstructioncited by 39
- 20233D Face Reconstruction with the Geometric Guidance of Facial Part Segmentationcited by 38
- 2023HAvatar: High-fidelity Head Avatar via Facial Model Conditioned Neural Radiance Fieldcited by 37
- 2025DreamActor-M1: Holistic, Expressive and Robust Human Image Animation with Hybrid Guidancecited by 36
- 2023HHAvatar: Gaussian Head Avatar with Dynamic Hairscited by 35
- 2023MonoNPHM: Dynamic Head Reconstruction from Monocular Videoscited by 35
- 2023HiFace: High-Fidelity 3D Face Reconstruction by Learning Static and Dynamic Detailscited by 22
- 2024TextToon: Real-Time Text Toonify Head Avatar from Single Videocited by 21
- 2023InvertAvatar: Incremental GAN Inversion for Generalized Head Avatarscited by 19
- 2025DreamActor-H1: High-Fidelity Human-Product Demonstration Video Generation via Motion-designed Diffusion Transformerscited by 19
- 2023MoSAR: Monocular Semi-Supervised Model for Avatar Reconstruction using Differentiable Shadingcited by 18
- 2023GANHead: Towards Generative Animatable Neural Head Avatarscited by 17
- 2023ReactFace: Online Multiple Appropriate Facial Reaction Generation in Dyadic Interactionscited by 17
- 2022Neural Parameterization for Dynamic Human Head Editingcited by 16
- 2023Single-Shot Implicit Morphable Faces with Consistent Texture Parameterizationcited by 16
- 2024REACT 2024: the Second Multiple Appropriate Facial Reaction Generation Challengecited by 16
- 2024Tri2-plane: Thinking Head Avatar via Feature Pyramidcited by 16
- 2025AvatarArtist: Open-Domain 4D Avatarizationcited by 15
- 202550 Years of Automated Face Recognitioncited by 13
- 2022BareSkinNet: De-makeup and De-lighting via 3D Face Reconstructioncited by 10
- 2024GPHM: Gaussian Parametric Head Model for Monocular Head Avatar Reconstructioncited by 10
- 2022Towards 3D Face Reconstruction in Perspective Projection: Estimating 6DoF Face Pose from Monocular Imagecited by 9
- 2024Spectrum AUC Difference (SAUCD): Human-aligned 3D Shape Evaluationcited by 9
- 2024DICE: End-to-end Deformation Capture of Hand-Face Interactions from a Single Imagecited by 9
- 2025OmniTalker: One-shot Real-time Text-Driven Talking Audio-Video Generation With Multimodal Style Mimickingcited by 9
- 2025REACT 2025: the Third Multiple Appropriate Facial Reaction Generation Challengecited by 9
- 2023Implicit Shape and Appearance Priors for Few-Shot Full Head Reconstructioncited by 8
- 2024Head360: Learning a Parametric 3D Full-Head for Free-View Synthesis in 360degcited by 8
- 2025ChatAnyone: Stylized Real-time Portrait Video Generation with Hierarchical Motion Diffusion Modelcited by 8
- 2022PhoMoH: Implicit Photorealistic 3D Models of Human Headscited by 7
- 2023Deformable Model-Driven Neural Rendering for High-Fidelity 3D Reconstruction of Human Heads Under Low-View Settingscited by 7
- 2023Semantify: Simplifying the Control of 3D Morphable Models using CLIPcited by 7
- 2024Makeup Prior Models for 3D Facial Makeup Estimation and Applicationscited by 7
- 2025FreeUV: Ground-Truth-Free Realistic Facial UV Texture Recovery via Cross-Assembly Inference Strategycited by 7
- 2025PanoLAM: Large Avatar Model for Gaussian Full-Head Synthesis from One-shot Unposed Imagecited by 7
50 most cited of 98 All 98 (JSON)
- 2026ResDiffFRG: Residual Diffusion for Multiple Appropriate Facial Reaction Generation27 Sep 2026
- 2026Monocular Avatar Reconstruction via Cascaded Diffusion Priors and UV-Space Differentiable Shading26 Jun 2026
- 2026REACT 2026: The Fourth Multiple Appropriate Facial Reaction Generation Challenge: Personalised MAFRG and Appropriate EEG Reaction Prediction6 Jun 2026
- 2026Self-Learning Expression Deformations for Data-Efficient Gaussian Avatars4 Jun 2026
- 2026High-Fidelity Single-Image Head Modeling with Industry-Grade Topology6 May 2026
- 2026Face Anything: 4D Face Reconstruction from Any Image Sequence21 Apr 2026
- 2026PortraitDirector: A Hierarchical Disentanglement Framework for Controllable and Real-time Facial Reenactment21 Apr 2026
- 2026Giving Faces Their Feelings Back: Explicit Emotion Control for Feedforward Single-Image 3D Head Avatars16 Apr 2026
- 2026DipGuava: Disentangling Personalized Gaussian Features for 3D Head Avatars from Monocular Video30 Mar 2026
- 2026LiftAvatar: Kinematic-Space Completion for Expression-Controlled 3D Gaussian Avatar Animation2 Mar 2026
- 2026GeoDiff4D: Geometry-Aware Diffusion for 4D Head Avatar Reconstruction27 Feb 2026
- 2026Neu-PiG: Neural Preconditioned Grids for Fast Dynamic Surface Reconstruction on Long Sequences25 Feb 2026
38 more
- 2026SelfieAvatar: Real-time Head Avatar reenactment from a Selfie Video26 Jan 2026
- 2026KaoLRM: Repurposing Pre-trained Large Reconstruction Models for Parametric 3D Face Reconstruction19 Jan 2026
- 2025Using Gaussian Splats to Create High-Fidelity Facial Geometry and Texture18 Dec 2025
- 2025DeX-Portrait: Disentangled and Expressive Portrait Animation via Explicit and Latent Motion Representations17 Dec 2025
- 2025SRAM: Shape-Realism Alignment Metric for No Reference 3D Shape Evaluation1 Dec 2025
- 2025Bringing Your Portrait to 3D Presence27 Nov 2025
- 2025Hi-Reco: High-Fidelity Real-Time Conversational Digital Humans16 Nov 2025
- 2025PercHead: Perceptual Head Model for Single-Image 3D Head Reconstruction & Editing4 Nov 2025
- 2025GLVD: Guided Learned Vertex Descent7 Oct 2025
- 2025ReactDiff: Fundamental Multiple Appropriate Facial Reaction Diffusion Model6 Oct 2025
- 2025BFSM: 3D Bidirectional Face-Skull Morphable Model29 Sep 2025
- 2025Preconditioned Deformation Grids22 Sep 2025
- 2025PanoLAM: Large Avatar Model for Gaussian Full-Head Synthesis from One-shot Unposed Image9 Sep 2025
- 2025GRMM: Real-Time High-Fidelity Gaussian Morphable Head Model with Learned Residuals2 Sep 2025
- 2025TCFNet: Bidirectional face-bone transformation via a Transformer-based coarse-to-fine point movement network20 Aug 2025
- 2025Learning Personalised Human Internal Cognition from External Expressive Behaviours for Real Personality Recognition31 Jul 2025
- 2025Controllable and Expressive One-Shot Video Head Swapping20 Jun 2025
- 2025DreamActor-H1: High-Fidelity Human-Product Demonstration Video Generation via Motion-designed Diffusion Transformers12 Jun 2025
- 202550 Years of Automated Face Recognition30 May 2025
- 2025Exploring Timeline Control for Facial Motion Generation27 May 2025
- 2025REACT 2025: the Third Multiple Appropriate Facial Reaction Generation Challenge22 May 2025
- 2025ReactDiff: Latent Diffusion for Facial Reaction Generation20 May 2025
- 2025OmniTalker: One-shot Real-time Text-Driven Talking Audio-Video Generation With Multimodal Style Mimicking3 Apr 2025
- 2025DreamActor-M1: Holistic, Expressive and Robust Human Image Animation with Hybrid Guidance2 Apr 2025
- 2025ChatAnyone: Stylized Real-time Portrait Video Generation with Hierarchical Motion Diffusion Model27 Mar 2025
- 2025AvatarArtist: Open-Domain 4D Avatarization25 Mar 2025
- 2025EmoHead: Emotional Talking Head via Manipulating Semantic Expression Parameters25 Mar 2025
- 2025FreeUV: Ground-Truth-Free Realistic Facial UV Texture Recovery via Cross-Assembly Inference Strategy21 Mar 2025
- 2025SRM-Hair: Single Image Head Mesh Reconstruction via 3D Morphable Hair8 Mar 2025
- 2024Towards Native Generative Model for 3D Head Avatar2 Oct 2024
- 2024TextToon: Real-Time Text Toonify Head Avatar from Single Video23 Sep 2024
- 2024FreeAvatar: Robust 3D Facial Animation Transfer by Learning an Expression Foundation Model20 Sep 2024
- 2024S2TD-Face: Reconstruct a Detailed 3D Face with Controllable Texture from a Single Sketch2 Aug 2024
- 2024Head360: Learning a Parametric 3D Full-Head for Free-View Synthesis in 360deg1 Aug 2024
- 2024GPHM: Gaussian Parametric Head Model for Monocular Head Avatar Reconstruction21 Jul 2024
- 2024DICE: End-to-end Deformation Capture of Hand-Face Interactions from a Single Image26 Jun 2024
- 2024Rank-based No-reference Quality Assessment for Face Swapping4 Jun 2024
- 2024DNPM: A Neural Parametric Model for the Synthesis of Facial Geometric Details30 May 2024
50 newest of 98 All 98 (JSON)
- 2023Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priorscited by 395
- 2025DreamActor-H1: High-Fidelity Human-Product Demonstration Video Generation via Motion-designed Diffusion Transformerscited by 19
- 2025AvatarArtist: Open-Domain 4D Avatarizationcited by 15
- 2025ChatAnyone: Stylized Real-time Portrait Video Generation with Hierarchical Motion Diffusion Modelcited by 8
- 2025ReactDiff: Fundamental Multiple Appropriate Facial Reaction Diffusion Modelcited by 4
- 2025ReactDiff: Latent Diffusion for Facial Reaction Generationcited by 2
- 2025DeX-Portrait: Disentangled and Expressive Portrait Animation via Explicit and Latent Motion Representationscited by 2
- 2026Monocular Avatar Reconstruction via Cascaded Diffusion Priors and UV-Space Differentiable Shadingcited by 1
- 2026Monocular Avatar Reconstruction via Cascaded Diffusion Priors and UV-Space Differentiable Shading26 Jun 2026
- 2025DeX-Portrait: Disentangled and Expressive Portrait Animation via Explicit and Latent Motion Representations17 Dec 2025
- 2025ReactDiff: Fundamental Multiple Appropriate Facial Reaction Diffusion Model6 Oct 2025
- 2025DreamActor-H1: High-Fidelity Human-Product Demonstration Video Generation via Motion-designed Diffusion Transformers12 Jun 2025
- 2025ReactDiff: Latent Diffusion for Facial Reaction Generation20 May 2025
- 2025ChatAnyone: Stylized Real-time Portrait Video Generation with Hierarchical Motion Diffusion Model27 Mar 2025
- 2025AvatarArtist: Open-Domain 4D Avatarization25 Mar 2025
- 2023Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priors30 Jun 2023
- 2022PyMAF-X: Towards Well-aligned Full-body Model Regression from Monocular Imagescited by 152
- 2022Next3D: Generative Neural Texture Rasterization for 3D-Aware Head Avatarscited by 124
- 2023MonoGaussianAvatar: Monocular Gaussian Point-based Head Avatarcited by 89
- 2023AvatarReX: Real-time Expressive Full-body Avatarscited by 83
- 2022KeypointNeRF: Generalizing Image-based Volumetric Avatars using Relative Spatial Encoding of Keypointscited by 77
- 2023DiffusionRig: Learning Personalized Priors for Facial Appearance Editingcited by 74
- 2022AvatarMAV: Fast 3D Head Avatar Reconstruction Using Motion-Aware Neural Voxelscited by 73
- 2022Learning Neural Parametric Head Modelscited by 73
- 2022ClipFace: Text-guided Editing of Textured 3D Morphable Modelscited by 59
- 2023StyleAvatar: Real-time Photo-realistic Portrait Avatar from a Single Videocited by 52
- 2022Visual Speech-Aware Perceptual 3D Facial Expression Reconstruction from Videoscited by 50
- 2023VividTalk: One-Shot Audio-Driven Talking Head Generation Based on 3D Hybrid Priorcited by 47
12 most cited of 90 All 90 (JSON)
- 2026ResDiffFRG: Residual Diffusion for Multiple Appropriate Facial Reaction Generation27 Sep 2026
- 2026REACT 2026: The Fourth Multiple Appropriate Facial Reaction Generation Challenge: Personalised MAFRG and Appropriate EEG Reaction Prediction6 Jun 2026
- 2026Self-Learning Expression Deformations for Data-Efficient Gaussian Avatars4 Jun 2026
- 2026High-Fidelity Single-Image Head Modeling with Industry-Grade Topology6 May 2026
- 2026Face Anything: 4D Face Reconstruction from Any Image Sequence21 Apr 2026
- 2026PortraitDirector: A Hierarchical Disentanglement Framework for Controllable and Real-time Facial Reenactment21 Apr 2026
- 2026Giving Faces Their Feelings Back: Explicit Emotion Control for Feedforward Single-Image 3D Head Avatars16 Apr 2026
- 2026DipGuava: Disentangling Personalized Gaussian Features for 3D Head Avatars from Monocular Video30 Mar 2026
- 2026LiftAvatar: Kinematic-Space Completion for Expression-Controlled 3D Gaussian Avatar Animation2 Mar 2026
- 2026GeoDiff4D: Geometry-Aware Diffusion for 4D Head Avatar Reconstruction27 Feb 2026
- 2026Neu-PiG: Neural Preconditioned Grids for Fast Dynamic Surface Reconstruction on Long Sequences25 Feb 2026
- 2026SelfieAvatar: Real-time Head Avatar reenactment from a Selfie Video26 Jan 2026
12 newest of 90 All 90 (JSON)