FLAME-Universe

FLAME is a lightweight and expressive generic head model learned from over 33,000 of accurately aligned 3D scans. FLAME combines a linear identity shape space (trained from head scans of 3800 subjects) with an articulated neck, jaw, and eyeballs, pose-dependent corrective blendshapes, and additional global expression blendshapes. For details please see the scientific publication.

To download the FLAME model, sign up under MPI-IS/FLAME and agree to the model license. Then you can download FLAME and other FLAME-related resources such as landmark embeddings, segmentation masks, quad template mesh, etc., from MPI-IS/FLAME/download. You can also download the model with a bash script such as fetch_FLAME.

• BFM_to_FLAME: Conversion from Basel Face Model (BFM) to FLAME.
• CVTHead: Controllable head avatar generation from a single image.
• DECA: Reconstruction of 3D faces with animatable facial expression detail from a single image.
• DiffPoseTalk: Speech-driven stylistic 3D facial animation.
• diffusion-rig: Personalized model to edit facial expressions, head pose, and lighting in portrait images.
• EMOCA: Reconstruction of emotional 3D faces from a single image.
• EMOTE: Emotional speech-driven 3D face animation.
• expgan: Face image generation with expression control.
• FaceFormer: Speech-driven facial animation of meshes in FLAME mesh topology.
• FateAvatar: Full-head Gaussian Avatar with Textural Editing from Monocular Video.
• FLAME-Blender-Add-on: FLAME Blender Add-on.
• flame-fitting: Fitting of FLAME to scans.
• flame-head-tracker: FLAMe-based monocular video tracking.
• FLAME_PyTorch: FLAME PyTorch layer.
• GANHead: Animatable neural head avatar.
• GAGAvatar: Recontruction of controllable 3D head avatars from a single image.
• GaussianAvatars: Photorealistic head avatars with FLAME-rigged 3D Gaussians.
• GPAvatar: Prediction of controllable 3D head avatars from one or several images.
• GIF: Generating face images with FLAME parameter control.
• INSTA: Volumetric head avatars from videos in less than 10 minutes.
• INSTA-pytorch: Volumetric head avatars from videos in less than 10 minutes (PyTorch).
• learning2listen: Modeling interactional communication in dyadic conversations.
• LightAvatar-TensorFlow: Use of neural light field (NeLF) to build photorealistic 3D head avatars.
• MICA: Reconstruction of metrically accurated 3D faces from a single image.
• MeGA: Reconstruction of an editable hybrid mesh-Gaussian head avatar.
• metrical-tracker: Metrical face tracker for monocular videos.
• MultiTalk: Speech-driven facial animation of meshes in FLAME mesh topology.
• NED: Facial expression of emotion manipulation in videos.
• Next3D: 3D generative model with FLAME parameter control.
• NeuralHaircut: Creation of strand-based hairstyle from single-view or multi-view videos.
• neural-head-avatars: Building a neural head avatar from video sequences.
• NeRSemble: Building a neural head avatar from multi-view video data.
• photometric_optimization: Fitting of FLAME to images using differentiable rendering.-
• RGBAvatar: Reduced Gaussian Blendshapes for Online Modeling of Head Avatars.
• RingNet: Reconstruction of 3D faces from a single image.
• ROME: Creation of personalized avatar from a single image.
• SAFA: Animation of face images.
• Semantify: Semantic control over 3DMM parameters.
• SPARK: Personalized Real-time Monocular Face Capture
• SPECTRE: Speech-aware 3D face reconstruction from images.
• SplattingAvatar: Real-time human avatars with mesh-embedded Gaussian splatting.
• TalkingStyle: Personalized spech-driven 3D facial animation of meshes in FLAME mesh topology.
• SMIRK: Reconstruction of emotional 3D faces from a single image.
• TRUST: Racially unbiased skin tone extimation from images.
• TF_FLAME: Fit FLAME to 2D/3D landmarks, FLAME meshes, or sample textured meshes.
• video-head-tracker: Track 3D heads in video sequences.
• VOCA: Speech-driven facial animation of meshes in FLAME mesh topology.
• VHAP: 3D face tracker for single-view and multi-view videos.

• BP4D+: 127 subjects, one neutral expression mesh each.
• CoMA dataset: 12 subjects, 12 extreme dynamic expressions each.
• D3DFACS: 10 subjects, 519 dynamic expressions in total.
• Decaf dataset: Deformation capture for face and hand interactions.
• FaceWarehouse: 150 subjects, one neutral expression mesh each.
• FaMoS: 95 subjects, 28 dynamic expressions and head poses each, about 600K frames in total.
• Florence 2D/3D: 53 subjects, one neutral expression mesh each.
• FRGC: 531 subjects, one neutral expression mesh each.
• LYHM: 1216 subjects, one neutral expression mesh each.
• MEAD reconstructions: 3D face reconstructions for MEAD (emotional talking-face dataset).
• MEAD-3D: FLAME meshes and model parameters for MEAD.
• NeRSemble dataset: 10 sequences of multi-view images and 3D faces in FLAME mesh topology.
• RenderMe-360: Digital asset library for high-fidelity head avatars with labeled FLAME parameters.
• SingingHead: 27 hours of synchronized singing video, audio, 3D facial motion, and background music from 76 subjects.
• Stirling: 133 subjects, one neutral expression mesh each.
• VOCASET: 12 subjects, 40 speech sequences each with synchronized audio.

2026

• GeoDiff4D: Geometry-Aware Diffusion for 4D Head Avatar Reconstruction.
• Combining Facial Videos and Biosignals for Stress Estimation During Driving.
• RSATalker: Realistic Socially-Aware Talking Head Generation for Multi-Turn Conversation.
• MANGO:Natural Multi-speaker 3D Talking Head Generation via 2D-Lifted Enhancement.
• An Interactive Conversational 3D Virtual Human.
• Generalizable and Animatable 3D Full-Head Gaussian Avatar from a Single Image.
• 3DGeoMeshNet: A multi-scale graph auto-encoder for 3D mesh reconstruction and completion.

2025

• VASA-3D: Lifelike Audio-Driven Gaussian Head Avatars from a Single Image.
• FIELDS: Face reconstruction with accurate Inference of Expression using Learning with Direct Supervision.
• ArchitectHead: Continuous Level of Detail Control for 3D Gaussian Head Avatars.
• GRMM: Real-Time High-Fidelity Gaussian Morphable Head Model with Learned Residuals.
• FastAvatar: Towards Unified Fast High-Fidelity 3D Avatar Reconstruction with Large Gaussian Reconstruction Transformers.
• OT-Talk: Animating 3D Talking Head with Optimal Transportation.
• SEGA: Drivable 3D Gaussian Head Avatar from a Single Image.
• ARTalk: Speech-Driven 3D Head Animation via Autoregressive Model
• TEASER: Token Enhanced Spatial Modeling For Expressions Reconstruction.
• PrismAvatar: Real-time animated 3D neural head avatars on edge devices.
• TalkingEyes: Pluralistic Speech-Driven 3D Eye Gaze Animation.
• EcoFace: Audio-Visual Emotional Co-Disentanglement Speech-Driven 3D Talking Face Generation (ICLR 2025).
• MeGA: Hybrid Mesh-Gaussian Head Avatar for High-Fidelity Rendering and Head Editing (CVPR 2025).
• Data Synthesis with Diverse Styles for Face Recognition via 3DMM-Guided Diffusion (CVPR 2025).
• 3D Gaussian Head Avatars with Expressive Dynamic Appearances by Compact Tensorial Representations (CVPR 2025).
• Perceptually Accurate 3D Talking Head Generation: New Definitions, Speech-Mesh Representation, and Evaluation Metrics (CVPR 2025).
• DualTalk: Dual-Speaker Interaction for 3D Talking Head Conversations (CVPR 2025).
• Arc2Avatar: Generating Expressive 3D Avatars from a Single Image via ID Guidance (CVPR 2025).
• RGBAvatar: Reduced Gaussian Blendshapes for Online Modeling of Head Avatars (CVPR 2025).
• Coherent 3D Portrait Video Reconstruction via Triplane Fusion (CVPR 2025).
• ControlFace: Harnessing Facial Parametric Control for Face Rigging (CVPR 2025).
• GAF: Gaussian Avatar Reconstruction from Monocular Videos via Multi-view Diffusion (CVPR 2025).
• GPAvatar: High-fidelity Head Avatars by Learning Efficient Gaussian Projections (CVPR 2025).
• FATE: Full-head Gaussian Avatar with Textural Editing from Monocular Video (CVPR 2025).
• Gaussian Eigen Models for Human Heads (CVPR 2025).
• Electromyography-Informed Facial Expression Reconstruction for Physiological-Based Synthesis and Analysis (CVPR 2025).
• CAP4D: Creating Animatable 4D Portrait Avatars with Morphable Multi-View Diffusion Models (CVPR 2025).
• OFER: Occluded Face Expression Reconstruction (CVPR 2025).
• Gaussian Déjà-vu: Creating Controllable 3D Gaussian Head-Avatars with Enhanced Generalization and Personalization Abilities (WACV 2025).
• EmoVOCA: Speech-Driven Emotional 3D Talking Heads (WACV 2025).
• DEEPTalk: Dynamic Emotion Embedding for Probabilistic Speech-Driven 3D Face Animation (AAAI 2025).

2024

• GaussianHair: Hair Modeling and Rendering with Light-aware Gaussians.
• FATE: Full-head Gaussian Avatar with Textural Editing from Monocular Video.
• SurFhead: Affine Rig Blending for Geometrically Accurate 2D Gaussian Surfel Head Avatars.
• MixedGaussianAvatar: Realistically and Geometrically Accurate Head Avatar via Mixed 2D-3D Gaussian Splatting.
• GaussianSpeech: Audio-Driven Gaussian Avatars.
• GaussianHeads: End-to-End Learning of Drivable Gaussian Head Avatars from Coarse-to-fine Representations.
• VGG-Tex: A Vivid Geometry-Guided Facial Texture Estimation Model for High Fidelity Monocular 3D Face Reconstruction.
• FAGhead: Fully Animate Gaussian Head from Monocular Videos.
• Rig3DGS: Creating Controllable Portraits from Casual Monocular Videos.
• ProbTalk3D: Non-Deterministic Emotion Controllable Speech-Driven 3D Facial Animation Synthesis Using VQ-VAE (SIGGRAPH MIG 2024).
• GGHead: Fast and Generalizable 3D Gaussian Heads (SIGGRAPH Asia 2024).-
• Generalizable and Animatable Gaussian Head Avatar (NeurIPS 2024).
• SPARK: Self-supervised Personalized Real-time Monocular Face Capture (SIGGRAPH Asia 2024).
• MultiTalk: Enhancing 3D Talking Head Generation Across Languages with Multilingual Video Dataset (INTERSPEECH 2024).
• GPAvatar: Generalizable and Precise Head Avatars from Image(S) (ICLR 2024).
• LightAvatar: Efficient Head Avatar as Dynamic Neural Light Field (ECCV-W 2024).
• Stable Video Portraits (ECCV 2024).
• GRAPE: Generalizable and Robust Multi-view Facial Capture (ECCV 2024.
• Human Hair Reconstruction with Strand-Aligned 3D Gaussians (ECCV 2024).
• PAV: Personalized Head Avatar from Unstructured Video Collection (ECCV 2024).
• GAUSSIAN3DIFF: 3D Gaussian Diffusion for 3D Full Head Synthesis and Editing (ECCV 2024).
• MeGA: Hybrid Mesh-Gaussian Head Avatar for High-Fidelity Rendering and Head Editing (ECCV 2024).
• HeadGaS: Real-Time Animatable Head Avatars via 3D Gaussian Splatting (ECCV 2024).
• HeadStudio: Text to Animatable Head Avatars with 3D Gaussian Splatting (ECCV 2024).
• 3D Gaussian Blendshapes for Head Avatar Animation (SIGGRAPH 2024).
• MonoGaussianAvatar: Monocular Gaussian Point-based Head Avatar (SIGGRAPH 2024).
• DiffPoseTalk: Speech-Driven Stylistic 3D Facial Animation and Head Pose Generation via Diffusion Models (SIGGRAPH 2024).
• EMAGE: Towards Unified Holistic Co-Speech Gesture Generation via Expressive Masked Audio Gesture Modeling (CVPR 2024).
• UltrAvatar: A Realistic Animatable 3D Avatar Diffusion Model with Authenticity Guided Textures (CVPR 2024).
• FlashAvatar: High-fidelity Head Avatar with Efficient Gaussian Embedding (CVPR 2024).
• Portrait4D: Learning One-Shot 4D Head Avatar Synthesis using Synthetic Data (CVPR 2024).
• SplattingAvatar: Realistic Real-Time Human Avatars with Mesh-Embedded Gaussian Splatting (CVPR 2024).
• 3D Facial Expressions through Analysis-by-Neural-Synthesis (CVPR 2024).
• GaussianAvatars: Photorealistic Head Avatars with Rigged 3D Gaussians (CVPR 2024).
• FaceComposer: A Unified Model for Versatile Facial Content Creation (NeurIPS 2023).
• Feel the Bite: Robot-Assisted Inside-Mouth Bite Transfer using Robust Mouth Perception and Physical Interaction-Aware Control (HRI 2024).
• ReliTalk: Relightable Talking Portrait Generation from a Single Video (IJCV 2024).
• Audio-Driven Speech Animation with Text-Guided Expression (EG 2024).
• CVTHead: One-shot Controllable Head Avatar with Vertex-feature Transformer (WACV 2024).
• AU-Aware Dynamic 3D Face Reconstruction from Videos with Transformer (WACV 2024).
• Towards Realistic Generative 3D Face Models (WACV 2024).
• LaughTalk: Expressive 3D Talking Head Generation with Laughter (WACV 2024).
• NeRFlame: FLAME-based conditioning of NeRF for 3D face rendering (ICCS 2024).

2023

• A Large-Scale 3D Face Mesh Video Dataset via Neural Re-parameterized Optimization.
• DF-3DFace: One-to-Many Speech Synchronized 3D Face Animation with Diffusion
• HeadCraft: Modeling High-Detail Shape Variations for Animated 3DMMs.
• 3DiFACE: Diffusion-based Speech-driven 3D Facial Animation and Editing.
• Articulated 3D Head Avatar Generation using Text-to-Image Diffusion Models.
• Fake It Without Making It: Conditioned Face Generation for Accurate 3D Face.
• Text2Face: A Multi-Modal 3D Face Model.
• SelfTalk: A Self-Supervised Commutative Training Diagram to Comprehend 3D Talking Faces (ACM-MM 2023).
• Expressive Speech-driven Facial Animation with controllable emotions (ICMEW 2023).
• A Perceptual Shape Loss for Monocular 3D Face Reconstruction (Pacific Graphics 2023).
• FLARE: Fast Learning of Animatable and Relightable Mesh Avatars (SIGGRAPH Asia 2023).
• Emotional Speech-Driven Animation with Content-Emotion Disentanglement (SIGGRAPH Asia 2023).
• Decaf: Monocular Deformation Capture for Face and Hand Interactions (SIGGRAPH Asia 2023).
• Neural Haircut: Prior-Guided Strand-Based Hair Reconstruction (ICCV 2023).
• Can Language Models Learn to Listen? (ICCV 2023).
• Accurate 3D Face Reconstruction with Facial Component Tokens (ICCV 2023)
• Speech4Mesh: Speech-Assisted Monocular 3D Facial Reconstruction for Speech-Driven 3D Facial Animation (ICCV 2023).
• Semantify: Simplifying the Control of 3D Morphable Models using CLIP (ICCV 2023).
• Imitator: Personalized Speech-driven 3D Facial Animation (ICCV 2023).
• NeRSemble: Multi-view Radiance Field Reconstruction of Human Heads (SIGGRAPH 2023).
• ClipFace: Text-guided Editing of Textured 3D Morphable Models (SIGGRAPH 2023).
• SunStage: Portrait Reconstruction and Relighting using the Sun as a Light Stage (CVPR 2023).
• GANHead: Towards Generative Animatable Neural Head Avatars (CVPR 2023).
• Implicit Neural Head Synthesis via Controllable Local Deformation Fields (CVPR 2023).
• DiffusionRig: Learning Personalized Priors for Facial Appearance Editing (CVPR 2023).
• High-Res Facial Appearance Capture from Polarized Smartphone Images (CVPR 2023).
• Instant Volumetric Head Avatars (CVPR 2023).
• Learning Personalized High Quality Volumetric Head Avatars (CVPR 2023).
• Next3D: Generative Neural Texture Rasterization for 3D-Aware Head Avatars (CVPR 2023).
• PointAvatar: Deformable Point-based Head Avatars from Videos (CVPR 2023).
• Visual Speech-Aware Perceptual 3D Facial Expression Reconstruction from Videos (CVPR-W 2023).
• Scaling Neural Face Synthesis to High FPS and Low Latency by Neural Caching (WACV 2023).

2022

• TeleViewDemo: Experience the Future of 3D Teleconferencing (SIGGRAPH Asia 2022).
• Realistic One-shot Mesh-based Head Avatars (ECCV 2022).
• Towards Metrical Reconstruction of Human Faces (ECCV 2022).
• Towards Racially Unbiased Skin Tone Estimation via Scene Disambiguation (ECCV 2022).
• Generative Neural Articulated Radiance Fields (NeurIPS 2022).
• EMOCA: Emotion Driven Monocular Face Capture and Animation (CVPR 2022).
• Generating Diverse 3D Reconstructions from a Single Occluded Face Image (CVPR 2022).
• I M Avatar: Implicit Morphable Head Avatars from Videos (CVPR 2022).
• Learning to Listen: Modeling Non-Deterministic Dyadic Facial Motion (CVPR 2022).
• Neural Emotion Director: Speech-preserving semantic control of facial expressions in “in-the-wild” videos (CVPR 2022).
• Neural head avatars from monocular RGB videos (CVPR 2022).
• RigNeRF: Fully Controllable Neural 3D Portraits (CVPR 2022).
• Simulated Adversarial Testing of Face Recognition Models (CVPR 2022).
• Accurate 3D Hand Pose Estimation for Whole-Body 3D Human Mesh Estimation (CVPR-W 2022).
• MOST-GAN: 3D Morphable StyleGAN for Disentangled Face Image Manipulation (AAAI 2022).
• Exp-GAN: 3D-Aware Facial Image Generation with Expression Control (ACCV 2022).

2021

• Data-Driven 3D Neck Modeling and Animation (TVCG 2021).
• MorphGAN: One-Shot Face Synthesis GAN for Detecting Recognition Bias (BMVC 2021).
• SIDER : Single-Image Neural Optimization for Facial Geometric Detail Recovery (3DV 2021).
• SAFA: Structure Aware Face Animation (3DV 2021).
• Learning an Animatable Detailed 3D Face Model from In-The-Wild Images (SIGGRAPH 2021).

2020

• Monocular Expressive Body Regression through Body-Driven Attention (ECCV 2020).
• GIF: Generative Interpretable Faces (3DV 2020).

2019

• Learning to Regress 3D Face Shape and Expression from an Image without 3D Supervision (CVPR 2019).