awesome 3d human reconstruction

https://github.com/rlczddl/awesome-3d-human-reconstruction#3D_human_whole_body

GitHub - rlczddl/awesome-3d-human-reconstruction

A curated list of related resources for 3d human reconstruction. Your contributions are welcome!

Contents

• papers
  • AIGC
  • nerf or pifu
  • geo fusion
  • photo
  • 3D human whole body
  • 3D human body
  • 3d human face
  • 3d human head
  • 3D human hand
  • 3d cloth
  • 3d hair
  • 3d teeth
  • 3d eyelids
• related papers
  • human mattting
  • pose estimation
  • registration
  • correspondence
  • application
  • texture
  • skin
  • talking head
  • uncategorized
• parametric model
  • body
  • face
  • head
  • hand
  • method
• dataset
  • face
  • hand
  • body
  • method
• others
• labs
• other related awesome
• survey

3d human

AIGC

• Rodin: A Generative Model for Sculpting 3D Digital Avatars Using Diffusion paper• DreamFace: Progressive Generation of Animatable 3D Faces under Text Guidance paper• High-fidelity 3D Face Generation from Natural Language Descriptions

nerf_or_pifu

• StereoPIFu: Depth Aware Clothed Human Digitization via Stereo Vision paper• Learning Implicit 3D Representations of Dressed Humans from Sparse Views paper• Animatable Neural Radiance Fields for Human Body Modeling paper• PaMIR: Parametric Model-Conditioned Implicit Representation for Image-based Human Reconstruction paper code• Neural Actor: Neural Free-view Synthesis of Human Actors with Pose Control paper&code• MoCo-Flow: Neural Motion Consensus Flow for Dynamic Humans in Stationary Monocular Cameras paper• DoubleField: Bridging the Neural Surface and Radiance Fields for High-fidelity Human Rendering paper• Bridge the Gap Between Model-based and Model-free Human Reconstruction paper• MetaAvatar: Learning Animatable Clothed Human Models from Few Depth Images paper• Animatable Neural Radiance Fields from Monocular RGB Video paper• Few-shot Neural Human Performance Rendering from Sparse RGBD Videos paper• Relightable Neural Video Portrait paper• FLAME-in-NeRF : Neural control of Radiance Fields for Free View Face Animation paper• ARCH++: Animation-Ready Clothed Human Reconstruction Revisited paper• Neural-GIF: Neural Generalized Implicit Functions for Animating People in Clothing paper• Neural Human Performer: Learning Generalizable Radiance Fields for Human Performance Rendering paper code• Topologically Consistent Multi-View Face Inference Using Volumetric Sampling paper• Creating and Reenacting Controllable 3D Humans with Differentiable Rendering paper• H-NeRF: Neural Radiance Fields for Rendering and Temporal Reconstruction of Humans in Motion paper• FENeRF: Face Editing in Neural Radiance Fields paper• LatentHuman: Shape-and-Pose Disentangled Latent Representation for Human Bodies paper&code• Neural Head Avatars from Monocular RGB Videos paper• HumanNeRF: Generalizable Neural Human Radiance Field from Sparse Inputs paper• Implicit Neural Deformation for Multi-View Face Reconstruction paper• MoFaNeRF: Morphable Facial Neural Radiance Field paper code• Geometry-Guided Progressive NeRF for Generalizable and Efficient Neural Human Rendering paper• HeadNeRF: A Real-time NeRF-based Parametric Head Model paper code• I M Avatar: Implicit Morphable Head Avatars from Videos paper code• LookinGoodπ: Real-time Person-independent Neural Re-rendering for High-quality Human Performance Capture paper• ICON: Implicit Clothed humans Obtained from Normals paper code• DD-NeRF: Double-Diffusion Neural Radiance Field as a Generalizable Implicit Body Representation paper• Human View Synthesis using a Single Sparse RGB-D Input paper• Surface-Aligned Neural Radiance Fields for Controllable 3D Human Synthesis paper• Embodied Hands: Modeling and Capturing Hands and Bodies Together paper• HumanNeRF: Free-viewpoint Rendering of Moving People from Monocular Video paper code• gDNA: Towards Generative Detailed Neural Avatars paper code• SelfRecon: Self Reconstruction Your Digital Avatar from Monocular Video paper• NeuVV: Neural Volumetric Videos with Immersive Rendering and Editing paper• Animatable Neural Radiance Fields for Modeling Dynamic Human Bodies paper code• DeepMultiCap: Performance Capture of Multiple Characters Using Sparse Multiview Cameras paper code• NeuralFusion: Neural Volumetric Rendering under Human-object Interactions paper• PINA: Learning a Personalized Implicit Neural Avatar from a Single RGB-D Video Sequence paper code• NeuMan: Neural Human Radiance Field from a Single Video paper• M Avatar: Implicit Morphable Head Avatars from Videos paper code• ImFace: A Nonlinear 3D Morphable Face Model with Implicit Neural Representations paper• COAP: Compositional Articulated Occupancy of People paper code• SunStage: Portrait Reconstruction and Relighting using the Sun as a Light Stage paper• LISA: Learning Implicit Shape and Appearance of Hands paper• Animatable Neural Radiance Fields from Monocular RGB-D paper• JIFF: Jointly-aligned Implicit Face Function for High Quality Single View Clothed Human Reconstruction paper• Generalizable Neural Performer: Learning Robust Radiance Fields for Human Novel View Synthesis paper• DANBO: Disentangled Articulated Neural Body Representations via Graph Neural Networks paper• Single-view 3D Body and Cloth Reconstruction under Complex Poses paper• KeypointNeRF: Generalizing Image-based Volumetric Avatars using Relative Spatial Encoding of Keypoints paper• H3D-Net: Few-Shot High-Fidelity 3D Head Reconstruction paper code• Photorealistic Monocular 3D Reconstruction of Humans Wearing Clothing paper• High-Fidelity Human Avatars from a Single RGB Camera paper• UV Volumes for Real-time Rendering of Editable Free-view Human Performance code• FOF: Learning Fourier Occupancy Field for Monocular Real-time Human Reconstruction paper• NeMF: Neural Motion Fields for Kinematic Animation paper• RigNeRF: Fully Controllable Neural 3D Portraits paper• EyeNeRF: A Hybrid Representation for Photorealistic Synthesis, Animation and Relighting of Human Eyes paper• TAVA: Template-free Animatable Volumetric Actors paper• Neural Surface Reconstruction of Dynamic Scenes with Monocular RGB-D Camera homepage• Generative Neural Articulated Radiance Fields paper• Neural Parameterization for Dynamic Human Head Editing paper• AvatarCap: Animatable Avatar Conditioned Monocular Human Volumetric Capture paper code• Learning Implicit Templates for Point-Based Clothed Human Modeling homepage•Relighting4D: Neural Relightable Human from Videos code•High Quality Human Reconstruction via Diffusion-based Stereo Using Sparse Cameras paper•CrossHuman: Learning Cross-Guidance from Multi-Frame Images for Human Reconstruction paper•UNIF: United Neural Implicit Functions for Clothed Human Reconstruction and Animation paper code•Drivable Volumetric Avatars using Texel-Aligned Features paper•The One Where They Reconstructed 3D Humans and Environments in TV Shows homepage•AvatarGen: a 3D Generative Model for Animatable Human Avatars paper•VolTeMorph: Realtime, Controllable and Generalisable Animation of Volumetric Representations paper•Multi-NeuS: 3D Head Portraits from Single Image with Neural Implicit Functions paper•Learning to Relight Portrait Images via a Virtual Light Stage and Synthetic-to-Real Adaptation paper•Occupancy Planes for Single-view RGB-D Human Reconstruction Xiaoming Zhao, Yuan-Ting Hu, Zhongzheng Ren, Alexander G. Schwing paper•ManVatar : Fast 3D Head Avatar Reconstruction Using Motion-Aware Neural Voxels paper•NeuS2: Fast Learning of Neural Implicit Surfaces for Multi-view Reconstruction paper•Structured 3D Features for Reconstructing Relightable and Animatable Avatars project•PhoMoH: Implicit Photorealistic 3D Models of Human Heads paper•NerfCap: Human Performance Capture With Dynamic Neural Radiance Fields paper code•ECON: Explicit Clothed humans Obtained from Normals homepage•PointAvatar: Deformable Point-based Head Avatars from Videos homepage•TotalSelfScan: Learning Full-body Avatars from Self-Portrait Videos of Faces, Hands, and Bodies project•InstantAvatar: Learning Avatars from Monocular Video in 60 Seconds homepage•HumanGen: Generating Human Radiance Fields with Explicit Priors paper• GazeNeRF: 3D-Aware Gaze Redirection with Neural Radiance Fields paper• Pixel2ISDF: Implicit Signed Distance Fields based Human Body Model from Multi-view and Multi-pose Images paper• Learning Neural Parametric Head Models homepage• RANA: Relightable Articulated Neural Avatars paper• One-shot Implicit Animatable Avatars with Model-based Priors paper• Super-resolution 3D Human Shape from a Single Low-Resolution Image paper code• Vid2Avatar: 3D Avatar Reconstruction from Videos in the Wild via Self-supervised Scene Decomposition paper• X-Avatar: Expressive Human Avatars github• Learning Neural Volumetric Representations of Dynamic Humans in Minutes paper&code• NeRSemble: Multi-view Radiance Field Reconstruction of Human Heads paper

geo_fusion

• DoubleFusion: Real-time Capture of Human Performances with Inner Body Shapes from a Single Depth Sensor paper• Robust 3D Self-portraits in Seconds paper• ACCURATE HUMAN BODY RECONSTRUCTION FOR VOLUMETRIC VIDEO paper• OcclusionFusion: Occlusion-aware Motion Estimation for Real-time Dynamic 3D Reconstruction paper code

photo

• Portrait Reconstruction and Relighting using the Sun as a Light Stage homepage• Reconstructing Hand-Held Objects from Monocular Video paper• In-Hand 3D Object Scanning from an RGB Sequence paper

3D_human_whole_body

• Monocular Expressive Body Regression through Body-Driven Attention paper code• FrankMocap: Fast Monocular 3D Hand and Body Motion Capture by Regression and Integration paper code• Collaborative Regression of Expressive Bodies using Moderation paper&code• Monocular Real-time Full Body Capture with Inter-part Correlations paper&code• Monocular Real-time Hand Shape and Motion Capture using Multi-modal Data paper&code• Real-time RGBD-based Extended Body Pose Estimation paper code• Detailed Avatar Recovery from Single Image paper• Lightweight Multi-person Total Motion Capture Using Sparse Multi-view Cameras paper• Imposing Temporal Consistency on Deep Monocular Body Shape and Pose Estimation paper• PIANO: A Parametric Hand Bone Model from Magnetic Resonance Imaging github• GOAL: Generating 4D Whole-Body Motion for Hand-Object Grasping paper code• PyMAF-X: Towards Well-aligned Full-body Model Regression from Monocular Images paper• Generating Holistic 3D Human Motion from Speech project• One-Stage 3D Whole-Body Mesh Recovery with Component Aware Transformer project

3D_human_body

• Pose2Mesh: Graph Convolutional Network for 3D Human Pose and Mesh Recovery from a 2D Human Pose paper code• Monocular Real-Time Volumetric Performance Capture paper code• Full-Body Awareness from Partial Observations paper code• CenterHMR: a Bottom-up Single-shot Method for Multi-person 3D Mesh Recovery from a Single Image paper code• Reconstructing NBA players paper code• Going beyond Free Viewpoint: Creating Animatable Volumetric Video of Human Performances paper• Synthetic Training for Accurate 3D Human Pose and Shape Estimation in the Wild paper code• MonoClothCap: Towards Temporally Coherent Clothing Capture from Monocular RGB Video paper• Multi-View Consistency Loss for Improved Single-Image 3D Reconstruction of Clothed People paper code• Synthetic Training for Monocular Human Mesh Recovery paper• Pose2Pose: 3D Positional Pose-Guided 3D Rotational Pose Prediction for Expressive 3D Human Pose and Mesh Estimation paper• Deep Physics-aware Inference of Cloth Deformation for Monocular Human Performance Capture• 4D Human Body Capture from Egocentric Video via 3D Scene Grounding paper• HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimation paper code• We are More than Our Joints: Predicting how 3D Bodies Move paper• SMPLy Benchmarking 3D Human Pose Estimation in the Wild paper• Synthesizing Long-Term 3D Human Motion and Interaction in 3D paper• Detailed 3D Human Body Reconstruction from Multi-view Images Combining Voxel Super-Resolution and Learned Implicit Representation• A novel joint points and silhouette-based method to estimate 3D human pose and shape• FaceDet3D: Facial Expressions with 3D Geometric Detail Prediction paper• NerFACE: Dynamic Neural Radiance Fields for Monocular 4D Facial Avatar Reconstruction code• Learning Complex 3D Human Self-Contact paper• Populating 3D Scenes by Learning Human-Scene Interaction paper• ANR: Articulated Neural Rendering for Virtual Avatars paper• Human Mesh Recovery from Multiple Shots paper• Lifting 2D StyleGAN for 3D-Aware Face Generation [paper](S3: Neural Shape, Skeleton, and Skinning Fields for 3D Human Modeling)• Capturing Detailed Deformations of Moving Human Bodies paper• 3D Human Pose, Shape and Texture from Low-Resolution Images and Videos paper• ChallenCap: Monocular 3D Capture of Challenging Human Performances using Multi-Modal References paper• SMPLicit: Topology-aware Generative Model for Clothed People paper&code• Learning High Fidelity Depths of Dressed Humans by Watching Social Media Dance Videos paper• NeuralHumanFVV: Real-Time Neural Volumetric Human Performance Rendering using RGB Cameras paper• Probabilistic 3D Human Shape and Pose Estimation from Multiple Unconstrained Images in the Wild paper• 3DCrowdNet: 2D Human Pose-Guided 3D Crowd Human Pose and Shape Estimation in the Wild paper• SCALE: Modeling Clothed Humans with a Surface Codec of Articulated Local Elements paper• Multi-person Implicit Reconstruction from a Single Image paper• PARE: Part Attention Regressor for 3D Human Body Estimation paper code• Temporal Consistency Loss for High Resolution Textured and Clothed 3D Human Reconstruction from Monocular Video paper• Function4D: Real-time Human Volumetric Capture from Very Sparse Consumer RGBD Sensors paper• End-to-End Human Pose and Mesh Reconstruction with Transformers paper• Revitalizing Optimization for 3D Human Pose and Shape Estimation: A Sparse Constrained Formulation paper• SHARP: Shape-Aware Reconstruction of People In Loose Clothing paper• THUNDR: Transformer-based 3D HUmaN Reconstruction with Markers paper• Deep3DPose: Realtime Reconstruction of Arbitrarily Posed Human Bodies from Single RGB Images paper• Learning Local Recurrent Models for Human Mesh Recovery paper• PoseFusion2: Simultaneous Background Reconstruction and Human Shape Recovery in Real-time paper• LASOR: Learning Accurate 3D Human Pose and Shape Via Synthetic Occlusion-Aware Data and Neural Mesh Rendering paper• Learning Motion Priors for 4D Human Body Capture in 3D Scenes paper code• Probabilistic Modeling for Human Mesh Recovery paper&code• DC-GNet: Deep Mesh Relation Capturing Graph Convolution Network for 3D Human Shape Reconstruction paper• Encoder-decoder with Multi-level Attention for 3D Human Shape and Pose Estimation paper code• Action-Conditioned 3D Human Motion Synthesis with Transformer VAE code• Learning to Regress Bodies from Images using Differentiable Semantic Rendering paper• Deep Two-Stream Video Inference for Human Body Pose and Shape Estimation paper• UltraPose: Synthesizing Dense Pose with 1 Billion Points by Human-body Decoupling 3D Model paper• Body Size and Depth Disambiguation in Multi-Person Reconstruction from Single Images paper code• Unified 3D Mesh Recovery of Humans and Animals by Learning Animal Exercise paper• 3D Human Shape and Pose from a Single Low-Resolution Image with Self-Supervised Learning paper code• Out-of-Domain Human Mesh Reconstruction via Bilevel Online Adaptation paper code• MeshLeTemp: Leveraging the Learnable Vertex-Vertex Relationship to Generalize Human Pose and Mesh Reconstruction for In-the-Wild Scenes paper• Monocular Human Shape and Pose with Dense Mesh-borne Local Image Features paper• Human Performance Capture from Monocular Video in the Wild paper• Probabilistic Estimation of 3D Human Shape and Pose with a Semantic Local Parametric Model paper• GLAMR: Global Occlusion-Aware Human Mesh Recovery with Dynamic Cameras paper code• MetaAvatar: Learning Animatable Clothed Human Models from Few Depth Images} paper code• EgoBody: Human Body Shape, Motion and Social Interactions from Head-Mounted Devices paper code• Putting People in their Place: Monocular Regression of 3D People in Depth paper• Multi-initialization Optimization Network for Accurate 3D Human Pose and Shape Estimation paper• moothNet: A Plug-and-Play Network for Refining Human Poses in Videos paper• HSPACE: Synthetic Parametric Humans Animated in Complex Environments paper• VoteHMR: Occlusion-Aware Voting Network for Robust 3D Human Mesh Recovery from Partial Point Clouds paper code• H4D: Human 4D Modeling by Learning Neural Compositional Representation paper• Capturing Humans in Motion: Temporal-Attentive 3D Human Pose and Shape Estimation from Monocular Video paper code• HybridCap: Inertia-aid Monocular Capture of Challenging Human Motions paper• Learning to Estimate Robust 3D Human Mesh from In-the-Wild Crowded Scenes paper code• BodySLAM: Joint Camera Localisation, Mapping, and Human Motion Tracking paper• HULC: 3D Human Motion Capture with Pose Manifold Sampling and Dense Contact Guidance paper• Learned Vertex Descent: A New Direction for 3D Human Model Fitting paper code• MUG: Multi-human Graph Network for 3D Mesh Reconstruction from 2D Pose paper• Accurate 3D Body Shape Regression using Metric and Semantic Attributes paper• Capturing and Inferring Dense Full-Body Human-Scene Contact homepage• Occluded Human Body Capture with Self-Supervised Spatial-Temporal Motion Prior paper• Live Stream Temporally Embedded 3D Human Body Pose and Shape Estimation paper code• CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape Estimation paper• FastMETRO: Cross-Attention of Disentangled Modalities for 3D Human Mesh Recovery with Transformers paper• Parametric Model Estimation for 3D Clothed Humans from Point Clouds paper code• Scene-Aware 3D Multi-Human Motion Capture from a Single Camera paper code• NeMo: 3D Neural Motion Fields from Multiple Video Instances of the Same Action homepage• IKOL: Inverse kinematics optimization layer for 3D human pose and shape estimation via Gauss-Newton differentiation paper code

3d_human_face

• High-Fidelity 3D Digital Human Creation from RGB-D Selfies paper code• StyleUV: Diverse and High-quality UV Map Generative Model paper• i3DMM: Deep Implicit 3D Morphable Model of Human Heads paper• Relightable 3D Head Portraits from a Smartphone Video paper• Learning Compositional Radiance Fields of Dynamic Human Heads paper• SIDER : Single-Image Neural Optimization for Facial Geometric Detail Recovery paper• Synergy between 3DMM and 3D Landmarks for Accurate 3D Facial Geometry paper code• HIGH-QUALITY REAL TIME FACIAL CAPTURE BASED ON SINGLE CAMERA paper• Self-supervised High-fidelity and Re-renderable 3D Facial Reconstruction from a Single Imag paper• Generating Diverse 3D Reconstructions from a Single Occluded Face Image paper• Self-Supervised Robustifying Guidance for Monocular 3D Face Reconstruction paper• BabyNet: Reconstructing 3D faces of babies from uncalibrated photographs paper• S2F2: Self-Supervised High Fidelity Face Reconstruction from Monocular Image paper• Facial Geometric Detail Recovery via Implicit Representation paper code• Beyond 3DMM: Learning to Capture High-fidelity 3D Face Shape paper• From 2D Images to 3D Model: Weakly Supervised Multi-View Face Reconstruction with Deep Fusion paper• F3D face reconstruction with dense landmarks paper• EMOCA: Emotion Driven Monocular Face Capture and Animation paper• Single-Image 3D Face Reconstruction under Perspective Projection paper• AVFace: Towards Detailed Audio-Visual 4D Face Reconstruction paper

3d_human_head

• Auto-Card: Auto-CARD: Efficient and Robust Codec Avatar Driving for Real-time Mobile Telepresence paper• DECA: Detailed Expression Capture and Animation paper code• Pixel Codec Avatars paper• H3D-Net: Few-Shot High-Fidelity 3D Head Reconstruction paper•Towards Metrical Reconstruction of Human Faces paper code•Data-driven 3D human head reconstruction paper•Dynamic 3D avatar creation from hand-held video input, ACM paper•Realistic One-shot Mesh-based Head Avatars paper•Authentic Volumetric Avatars from a Phone Scan paper•Neural Head Avatars from Monocular RGB Videos homepage•Towards Metrical Reconstruction of Human Faces homepage

3D_human_hand

• Active Learning for Bayesian 3D Hand Pose Estimation paper code• Multi-View Consistency Loss for Improved Single-Image 3D Reconstruction of Clothed People paper code• EventHands: Real-Time Neural 3D Hand Reconstruction from an Event Stream• Monocular Real-time Full Body Capture with Inter-part Correlations• Im2Mesh GAN: Accurate 3D Hand Mesh Recovery from a Single RGB Image• HandTailor: Towards High-Precision Monocular 3D Hand Recovery paper code• Camera-Space Hand Mesh Recovery via Semantic Aggregation and Adaptive 2D-1D Registration paper code• Model-based 3D Hand Reconstruction via Self-Supervised Learning paper code• Action-Conditioned 3D Human Motion Synthesis with Transformer VAE paper• Semi-Supervised 3D Hand-Object Poses Estimation with Interactions in Time paper• RGB2Hands: Real-Time Tracking of 3D Hand Interactions from Monocular RGB Video paper• ArtiBoost: Boosting Articulated 3D Hand-Object Pose Estimation via Online Exploration and Synthesis paper code• Monocular 3D Reconstruction of Interacting Hands via Collision-Aware Factorized Refinements paper code• Dynamic Iterative Refinement for Efficient 3D Hand Pose Estimation paper• Semi-Supervised 3D Hand Shape and Pose Estimation with Label Propagation paper• MobRecon: Mobile-Friendly Hand Mesh Reconstruction from Monocular Image paper code• Consistent 3D Hand Reconstruction in Video via Self-Supervised Learning paper• Interacting Attention Graph for Single Image Two-Hand Reconstruction paper• HandOccNet: Occlusion-Robust 3D Hand Mesh Estimation Network paper code• TOCH: Spatio-Temporal Object Correspondence to Hand for Motion Refinement paper• End-to-End 3D Hand Pose Estimation from Stereo Cameras paper• Efficient Annotation and Learning for 3DHand Pose Estimation: A Survey paper• 3D Interacting Hand Pose Estimation by Hand De-occlusion and Removal code

3d_cloth

• REC-MV: REconstructing 3D Dynamic Cloth from Monucular Videos github

3d_hair

• NeuralHDHair: Automatic High-fidelity Hair Modeling from a Single Image Using Implicit Neural Representations paper code•3D hair synthesis using volumetric variational autoencoders•AO-CNN: filament-aware hair reconstruction based on volumetric vector fields•Neural Strands: Learning Hair Geometry and Appearance from Multi-View Images paper•HairStep: Transfer Synthetic to Real Using Strand and Depth Maps for Single-View 3D Hair Modeling paper code

3d_teeth

• Model-based teeth reconstruction paper• An Implicit Parametric Morphable Dental Model project

3d_eyelids

• Real-time 3D Eyelids Tracking from Semantic Edges paper

3d foot

• FIND: An Unsupervised Implicit 3D Model of Articulated Human Feet project

related

human_mattting

• Real-Time High-Resolution Background Matting code• Real-Time Monocular Human Depth Estimation and Segmentation on Embedded Systems paper• DeepSportLab: a Unified Framework for Ball Detection, Player Instance Segmentation and Pose Estimation in Team Sports Scenes paper• PP-HumanSeg: Connectivity-Aware Portrait Segmentation with a Large-Scale Teleconferencing Video Dataset paper code• Portrait Segmentation Using Deep Learning paper• Human Instance Matting via Mutual Guidance and Multi-Instance Refinement paper code• 3DHumanGAN: Towards Photo-Realistic 3D-Aware Human Image Generation paper code• Test-time Adaptation vs. Training-time Generalization: A Case Study in Human Instance Segmentation using Keypoints Estimation paper• Body Segmentation Using Multi-task Learning paper

pose_estimation

• CanonPose: Self-Supervised Monocular 3D Human Pose Estimation in the Wild paper• Active Learning for Bayesian 3D Hand Pose Estimation paper code• A-NeRF: Surface-free Human 3D Pose Refinement via Neural Rendering• HandsFormer: Keypoint Transformer for Monocular 3D Pose Estimation of Hands and Object in Interaction paper• HuMoR: 3D Human Motion Model for Robust Pose Estimation paper• Multi-Person Extreme Motion Prediction with Cross-Interaction Attention paper• VoxelTrack: Multi-Person 3D Human Pose Estimation and Tracking in the Wild paper• Gravity-Aware Monocular 3D Human-Object Reconstruction paper&code• DensePose 3D: Lifting Canonical Surface Maps of Articulated Objects to the Third Dimension paper• Graph-Based 3D Multi-Person Pose Estimation Using Multi-View Images paper• Learning Dynamical Human-Joint Affinity for 3D Pose Estimation in Videos paper• Physics-based Human Motion Estimation and Synthesis from Videos paper• Real-time, low-cost multi-person 3D pose estimation paper• Direct Multi-view Multi-person 3D Human Pose Estimation paper code• Rethinking Keypoint Representations: Modeling Keypoints and Poses as Objects for Multi-Person Human Pose Estimation code• Camera Distortion-aware 3D Human Pose Estimation in Video with Optimization-based Meta-Learning paper• In-Bed Human Pose Estimation from Unseen and Privacy-Preserving Image Domains paper• Camera Motion Agnostic 3D Human Pose Estimation paper code• ElePose: Unsupervised 3D Human Pose Estimation by Predicting Camera Elevation and Learning Normalizing Flows on 2D Poses paper• Multi-modal 3D Human Pose Estimation with 2D Weak Supervision in Autonomous Driving paper• AdaptPose: Cross-Dataset Adaptation for 3D Human Pose Estimation by Learnable Motion Generation paper• FLAG: Flow-based 3D Avatar Generation from Sparse Observations paper• Pose-MUM : Reinforcing Key Points Relationship for Semi-Supervised Human Pose Estimation paper• Distribution-Aware Single-Stage Models for Multi-Person 3D Pose Estimation paper• P-STMO: Pre-Trained Spatial Temporal Many-to-One Model for 3D Human Pose Estimation paper code• PosePipe: Open-Source Human Pose Estimation Pipeline for Clinical Research paper code• 3D Human Pose Estimation Using Möbius Graph Convolutional Networks paper• Ray3D: ray-based 3D human pose estimation for monocular absolute 3D localization paper code• YOLO-Pose: Enhancing YOLO for Multi Person Pose Estimation Using Object Keypoint Similarity Loss paper code• Permutation-Invariant Relational Network for Multi-person 3D Pose Estimation paper• Non-Local Latent Relation Distillation for Self-Adaptive 3D Human Pose Estimation paper• Aligning Silhouette Topology for Self-Adaptive 3D Human Pose Recovery paper• Dite-HRNet: Dynamic Lightweight High-Resolution Network for Human Pose Estimation paper• PedRecNet: Multi-task deep neural network for full 3D human pose and orientation estimation paper• "Teaching Independent Parts Separately" (TIPS-GAN) : Improving Accuracy and Stability in Unsupervised Adversarial 2D to 3D Human Pose Estimation paper•Lightweight Human Pose Estimation Using Heatmap-Weighting Loss paper•VTP: Volumetric Transformer for Multi-view Multi-person 3D Pose Estimation paper•Location-free Human Pose Estimation paper•Trajectory Optimization for Physics-Based Reconstruction of 3d Human Pose from Monocular Video paper•SPGNet: Spatial Projection Guided 3D Human Pose Estimation in Low Dimensional Space paper•GraphMLP: A Graph MLP-Like Architecture for 3D Human Pose Estimation paper•BlazePose GHUM Holistic: Real-time 3D Human Landmarks and Pose Estimation paper•Mutual Adaptive Reasoning for Monocular 3D Multi-Person Pose Estimation paper•Human keypoint detection for close proximity human-robot interaction paper•VirtualPose: Learning Generalizable 3D Human Pose Models from Virtual Data paper•3D Clothed Human Reconstruction in the Wild paper code•EFFICIENT AND ACCURATE SKELETON-BASED TWO-PERSON INTERACTION RECOGNITION USING INTER- AND INTRA-BODY GRAPHS paper•Learning to Estimate 3D Human Pose from Point Cloud paper•Scene-aware Egocentric 3D Human Pose Estimation paper•Advanced Baseline for 3D Human Pose Estimation: A Two-Stage Approach paper•GFPose: Learning 3D Human Pose Prior with Gradient Fields paper•HUM3DIL: Semi-supervised Multi-modal 3D Human Pose Estimation for Autonomous Driving paper•TOWARDS SINGLE CAMERA HUMAN 3D-KINEMATICS paper•Markerless Body Motion Capturing for 3D Character Animation based on Multi-view Cameras paper•DiffuPose: Monocular 3D Human Pose Estimation via Denoising Diffusion Probabilistic Model paper•2D Human Pose Estimation with Explicit Anatomical Keypoints Structure Constraints paper•Weakly Supervised 3D Multi-person Pose Estimation for Large-scale Scenes based on Monocular Camera and Single LiDAR paper•Kinematic-aware Hierarchical Attention Network for Human Pose Estimation in Videos paper code•Proactive Multi-Camera Collaboration for 3D Human Pose Estimation homepage

registration

• LoopReg: Self-supervised Learning of Implicit Surface Correspondences, Pose and Shape for 3D Human Mesh Registration paper code• Neural Deformation Graphs for Globally-consistent Non-rigid Reconstruction paper code• FARM: Functional Automatic Registration Method for 3D Human Bodies paper code• Locally Aware Piecewise Transformation Fields for 3D Human Mesh Registration paper• Unsupervised 3D Human Mesh Recovery from Noisy Point Clouds paper

correspondence

• HumanGPS: Geodesic PreServing Feature for Dense Human Correspondences paper•BodyMap: Learning Full-Body Dense Correspondence Map paper•CorrI2P: Deep Image-to-Point Cloud Registration via Dense Correspondence paper

application

• One-Shot Free-View Neural Talking-Head Synthesis for Video Conferencing paper• LipSync3D: Data-Efficient Learning of Personalized 3D Talking Faces from Video using Pose and Lighting Normalization paper• ARShoe: Real-Time Augmented Reality Shoe Try-on System on Smartphones paper• A Neural Anthropometer Learning from Body Dimensions Computed on Human 3D Meshes paper• Robust 3D Garment Digitization from Monocular 2D Images for 3D Virtual Try-On Systems paper• Single-image Human-body Reshaping with Deep Neural Networks paper• Style-Based Global Appearance Flow for Virtual Try-On paper• Monitoring of Pigmented Skin Lesions Using 3D Whole Body Imaging paper• ESTIMATION OF 3D BODY SHAPE AND CLOTHING MEASUREMENTS FROM FRONTALAND SIDE-VIEW IMAGES paper• Dressing Avatars: Deep Photorealistic Appearance for Physically Simulated Clothing paper• AIFit: Automatic 3D Human-Interpretable Feedback Models for Fitness Training paper

texture

• Spatiotemporal Texture Reconstruction for Dynamic Objects Using a Single RGB-D Camera paper• Semi-supervised Synthesis of High-Resolution Editable Textures for 3D Humans paper• StylePeople: A Generative Model of Fullbody Human Avatars paper code• Refining 3D Human Texture Estimation from a Single Image paper

skin

• HeterSkinNet: A Heterogeneous Network for Skin Weights Prediction paper• SNARF: Differentiable Forward Skinning for Animating Non-Rigid Neural Implicit Shapes paper

lighting

• Relighting Humans in the Wild: Monocular Full-Body Human Relighting with Domain Adaptation code

talking_head

• DisCoHead: Audio-and-Video-Driven Talking Head Generation by Disentangled Control of Head Pose and Facial Expressions code• Imitator: Personalized Speech-driven 3D Facial Animation homepage• EmoTalk: Speech-driven emotional disentanglement for 3D face animation homepage

uncategorized

• Fully Convolutional Graph Neural Networks for Parametric Virtual Try-On paper• TailorNet: Predicting Clothing in 3D as a Function of Human Pose, Shape and Garment Style paper code• 3DBooSTeR: 3D Body Shape and Texture Recovery paper• Neural 3D Clothes Retargeting from a Single Image paper• Single-image Full-body Human Relighting paper• iButter: Neural Interactive Bullet Time Generator for Human Free-viewpoint Rendering paper• A Riemannian Framework for Analysis of Human Body Surface paper• The Power of Points for Modeling Humans in Clothing paper&code• Neural Human Deformation Transfer paper• 3D Human Texture Estimation from a Single Image with Transformers paper• Learning to Predict Diverse Human Motions from a Single Image via Mixture Density Networks paper• ZFlow: Gated Appearance Flow-based Virtual Try-on with 3D Priors paper• A Shading-Guided Generative Implicit Model for Shape-Accurate 3D-Aware Image Synthesis paper code• Action2video: Generating Videos of Human 3D Actions paper• Garment4D: Garment Reconstruction from Point Cloud Sequences paper code• ADG-Pose: Automated Dataset Generation for Real-World Human Pose Estimation paper code• DiffusionNet: Discretization Agnostic Learning on Surfaces paper• Text and Image Guided 3D Avatar Generation and Manipulation paper code• Quantification of Occlusion Handling Capability of a 3D Human Pose Estimation Framework paper• Motron: Multimodal Probabilistic Human Motion Forecasting paper• FEXGAN-META: FACIAL EXPRESSION GENERATION WITH META HUMANS paper• ActFormer: A GAN Transformer Framework towards General Action-Conditioned 3D Human Motion Generation• Domain Adaptive Hand Keypoint and Pixel Localization in the Wild paper• Portrait Eyeglasses and Shadow Removal by Leveraging 3D Synthetic Data paper• Recognition of Freely Selected Keypoints on Human Limbs paper• What’s in your hands? 3D Reconstruction of Generic Objects in Hands paper code• CHORE: Contact, Human and Object REconstruction from a single RGB image paper• SNUG: Self-Supervised Neural Dynamic Garments paper• 3D Magic Mirror: Clothing Reconstruction from a Single Image via a Causal Perspective paper• Fake it till you make it: face analysis in the wild using synthetic data alone homepage• AvatarCLIP: Zero-Shot Text-Driven Generation and Animation of 3D Avatars paper code• Scene Aware Person Image Generation through Global Contextual Conditioning paper• HairFIT: Pose-Invariant Hairstyle Transfer via Flow-based Hair Alignment and Semantic-Region-Aware Inpainting paper• From a few Accurate 2D Correspondences to 3D Point Clouds paper• Convolutional Neural Network Based Partial Face Detection paper• SPSN: Superpixel Prototype Sampling Network for RGB-D Salient Object Detection paper code• Detecting Humans in RGB-D Data with CNNs paper• Animation from Blur: Multi-modal Blur Decomposition with Motion Guidance paper• 3D Shape Sequence of Human Comparison and Classification using Current and Varifolds paper code• KinePose: A temporally optimized inverse kinematics technique for 6DOF human pose estimation with biomechanical constraints paper code• Skeleton-free Pose Transfer for Stylized 3D Character paper• Learning Continuous Mesh Representation with Spherical Implicit Surface paper• Scene Synthesis from Human Motion paper• Ego-Body Pose Estimation via Ego-Head Pose Estimation paper• Physically Plausible Animation of Human Upper Body from a Single Image paper

parametric model

body

• SMPL: A Skinned Multi-Person Linear Model paper code• Expressive Body Capture: 3D Hands, Face, and Body from a Single Image paper code• STAR: Sparse Trained Articulated Human Body Regressor paper code

face

• Basel Face Model 2009 website• Basel Face Model 2017 website• Large Scale 3D Morphable Model website• A Morphable Face Albedo Model github• Learning a 3D Morphable Face Reflectance Model from Low-cost Data paper code

head

• FLAME: Articulated Expressive Head Model website

hand

• MANO paper website• NIMBLE: A Non-rigid Hand Model with Bones and Muscles paper

method

•GHUM & GHUML: Generative 3D Human Shape and Articulated Pose Models github•Large Scale 3D Morphable Models paper code•Morphable Face Models - An Open Framework paper code

dataset

face

• MAAD-Face: A Massively Annotated Attribute Dataset for Face Images paper• FaceScape: 3D Facial Dataset and Benchmark for Single-View 3D Face Reconstruction paper• 300W-LP & AFLW2000-3D homepage• AFLW website• REALY: Rethinking the Evaluation of 3D Face Reconstruction paper website• FaceVerse-High Quality 3D Face Dataset github• DAD-3DHeads: A Large-scale Dense, Accurate and Diverse Dataset for 3D Head Alignment from a Single Image paper github• Multiface: A Dataset for Neural Face Rendering paper• DAD-3DHeads: A Large-scale Dense, Accurate and Diverse Dataset for 3D Head Alignment from a Single Image paper• mimicme github

hand

• GRAB: A Dataset of Whole-Body Human Grasping of Objects github• Reconstructing Hand-Object Interactions in the Wild github• Ego2HandsPose: A Dataset for Egocentric Two-hand 3D Global Pose Estimation paper• Interhand2.6M

body

• NTU60-X: TOWARDS SKELETON-BASED RECOGNITION OF SUBTLE HUMAN ACTIONS code• AGORA: Avatars in Geography Optimized for Regression Analysis homepage• AMASS: Archive of Motion Capture as Surface Shapes paper github• ASL-Skeleton3D and ASL-Phono: Two Novel Datasets for the American Sign Language paper•MPI-INF-3DHP homepage•Human3.6M website•3DPW website•PennAction website•Insta Variety github•PoseTrack homapage•Kinetics-400 website•RenderPeople website•BUFF website•People Snapshot Dataset homepage•Multi-Garment homepage•iPER website•ZJU-MoCap homepage•SmartPortraits: Depth Powered Handheld Smartphone Dataset of Human Portraits for State Estimation, Reconstruction and Synthesis paper•MVP-Human Dataset for 3D Human Avatar Reconstruction from Unconstrained Frames paper•HuMMan: Multi-Modal 4D Human Dataset for Versatile Sensing and Modeling paper github•3DMPB-dataset github•imar_vision_datasets_tools github•RICH: Real scenes, Interaction, Contacts and Humans github•Cloth3d github•DDH-QA arxiv•H3WB: Human3.6M 3D WholeBody Dataset and Benchmark github•LightStage homepage

method

•NeuralAnnot: Neural Annotator for 3D Human Mesh Training Sets paper

others

• K-Hairstyle: A Large-scale Korean hairstyle dataset for virtual hair editing and hairstyle classification homepage• Simulated garment dataset for virtual try-on address• DeepFashion homepage• Delving into High-Quality Synthetic Face Occlusion Segmentation Datasets paper• 3A-GAN: Facial Flow for Face Animation with Generative Adversarial Networks paper• Scanned Objects by Google Research website• EasyPortrait - Face Parsing and Portrait Segmentation Dataset github

labs

• max planck institute website• Yebin Liu website• ZJU3DV github• Hujun Bao google scholar• USTC-3DV homepage• Hao_Li homepage

other related awesome

• awesome-clothed-human github• curated-list-of-awesome-3D-Morphable-Model-software-and-data github• awesome-hand-pose-estimation github• Awesome 3D Body Papers github• Body_Reconstruction_References github• 3D-face-reconstruction-paper-list github• awesome_talking_face_generation github• CG&3DV Twitter github• FLAME-Universe github• human-motion-capture github

survey

• Recovering 3D Human Mesh from Monocular Images: A Survey paper github• 2D Human Pose Estimation: A Survey paper• A Survey of Non-Rigid 3D Registration paper• 3D Face Reconstruction in Deep Learning Era: A Survey paper• Towards efficient and photorealistic 3D human reconstruction: A brief survey paper•Survey on 3D face reconstruction from uncalibrated images paper•State of the Art on 3D Reconstruction with RGB-D Cameras paper