Skip to content

Latest commit

 

History

History
1028 lines (460 loc) · 70.4 KB

README_year.md

File metadata and controls

1028 lines (460 loc) · 70.4 KB

Awesome 3D Body Papers

Awesome

An awesome & curated list of papers about 3D human body.


Table of Contents


Body Model

Before 2018

SCAPE: Shape Completion and Animation of People. SIGGRAPH, 2005. [Page]

SMPL: A Skinned Multi-Person Linear Model. SIGGRAPH Asia, 2015. [Page] [Code]

2019

Expressive Body Capture: 3D Hands, Face, and Body from a Single Image. CVPR, 2019. [Page] [Code]

2020

GHUM & GHUML: Generative 3D Human Shape and Articulated Pose Models. CVPR (Oral), 2020. [Code]

BLSM: A Bone-Level Skinned Model of the Human Mesh. ECCV, 2020. [Page]

Joint Optimization for Multi-Person Shape Models from Markerless 3D-Scans. ECCV, 2020. [Code]

STAR: Sparse Trained Articulated Human Body Regressor. ECCV, 2020. [Page] [Code]

Modeling and Estimation of Nonlinear Skin Mechanics for Animated Avatars. Eurographics, 2020. [Page]

SoftSMPL: Data-driven Modeling of Nonlinear Soft-tissue Dynamics for Parametric Humans. Eurographics, 2020. [Page]

2021

LatentHuman: Shape-and-Pose Disentangled Latent Representation for Human Bodies. 3DV, 2021. [Page] [Code]

NPMs: Neural Parametric Models for 3D Deformable Shapes. ArXiv, 2021. [Page]

LEAP: Learning Articulated Occupancy of People. CVPR, 2021. [Page] [Code]

SCALE: Modeling Clothed Humans with a Surface Codec of Articulated Local Elements. CVPR, 2021. [Page]

SMPLicit: Topology-aware Generative Model for Clothed People. CVPR, 2021. [Page] [Code]

BASH: Biomechanical Animated Skinned Human for Visualization of Kinematics and Muscle Activity. GRAPP, 2021. [Code]

PanoMan: Sparse Localized Components–based Model for Full Human Motions. ToG, 2021.

2022

SUPR: A Sparse Unified Part-Based Human Representation. ECCV, 2022. [Page] [Code]

Body Pose

Before 2018

VNect: Real-time 3D Human Pose Estimation with a Single RGB Camera. SIGGRAPH Asia, 2017. [Page] [Code]

2019

MocapNET: Ensemble of SNN Encoders for 3D Human Pose Estimation in RGB Images. BMVC, 2019. [Code]

Fast and Robust Multi-Person 3D Pose Estimation from Multiple Views. CVPR, 2019. [Page] [Code]

Learnable Triangulation of Human Pose. ICCV (Oral), 2019. [Code]

2020

A Graph Attention Spatio-temporal Convolutional Networks for 3D Human Pose Estimation in Video. ArXiv, 2020. [Page] [Code]

Multi-person 3D Pose Estimation in Crowded Scenes Based on Multi-View Geometry. ArXiv, 2020. [Code]

PoP-Net: Pose over Parts Network for Multi-Person 3D Pose Estimation from a Depth Image. ArXiv, 2020. [Code]

PoseLifter: Absolute 3D Human Pose Lifting Network from a Single Noisy 2D Human Pose. ArXiv, 2020. [Code]

Temporal Smoothing for 3D Human Pose Estimation and Localization for Occluded People. ArXiv, 2020. [Code]

Cascaded Deep Monocular 3D Human Pose Estimation with Evolutionary Training Data. CVPR, 2020. [Code]

Compressed Volumetric Heatmaps for Multi-Person 3D Pose Estimation. CVPR, 2020. [Code]

Attention Mechanism Exploits Temporal Contexts: Real-time 3D Human Pose Reconstruction. CVPR (Oral), 2020. [Code]

DOPE: Distillation Of Part Experts for whole-body 3D pose estimation in the wild. ECCV, 2020. [Code]

SMAP: Single-Shot Multi-Person Absolute 3D Pose Estimation. ECCV, 2020. [Page] [Code]

SRNet: Improving Generalization in 3D Human Pose Estimation with a Split-and-Recombine Approach. ECCV, 2020. [Code]

Unsupervised 3D Human Pose Representation with Viewpoint and Pose Disentanglement. ECCV, 2020. [Code]

End-to-End Estimation of Multi-Person 3D Poses from Multiple Cameras. ECCV (Oral), 2020.

Residual Pose: A Decoupled Approach for Depth-based 3D Human Pose Estimation. IROS, 2020. [Code]

XNect: Real-time Multi-person 3D Human Pose Estimation with a Single RGB Camera. SIGGRAPH, 2020. [Page] [Code]

PhysCap: Physically Plausible Monocular 3D Motion Capture in Real Time. SIGGRAPH Asia, 2020. [Page] [Code]

MeTRAbs: Metric-Scale Truncation-Robust Heatmaps for Absolute 3D Human Pose Estimation. T-BIOM, 2020. [Page] [Code]

MotioNet: 3D Human Motion Reconstruction from Monocular Video with Skeleton Consistency. ToG, 2020. [Page] [Code]

2021

High Fidelity 3D Reconstructions with Limited Physical Views. 3DV, 2021. [Page] [Code]

Invariant Teacher and Equivariant Student for Unsupervised 3D Human Pose Estimation. AAAI, 2021. [Code]

3D Human Pose Estimation with Spatial and Temporal Transformers. ArXiv, 2021. [Code]

3D Human Reconstruction in the Wild with Collaborative Aerial Cameras. ArXiv, 2021. [Code]

FLEX: Parameter-free Multi-view 3D Human Motion Reconstruction. ArXiv, 2021. [Page]

MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimation. ArXiv, 2021. [Code]

PandaNet: Anchor-Based Single-Shot Multi-Person 3D Pose Estimation. ArXiv, 2021.

Real-time Lower-body Pose Prediction from Sparse Upper-body Tracking Signals. ArXiv, 2021.

Skeletor: Skeletal Transformers for Robust Body-Pose Estimation. ArXiv, 2021.

TriPose: A Weakly-Supervised 3D Human Pose Estimation via Triangulation from Video. ArXiv, 2021.

Weakly-supervised Cross-view 3D Human Pose Estimation. ArXiv, 2021.

CanonPose: Self-Supervised Monocular 3D Human Pose Estimation in the Wild. CVPR, 2021.

Context Modeling in 3D Human Pose Estimation: A Unified Perspective. CVPR, 2021.

FCPose: Fully Convolutional Multi-Person Pose Estimation with Dynamic Instance-Aware Convolutions. CVPR, 2021. [Code]

Monocular 3D Multi-Person Pose Estimation by Integrating Top-Down and Bottom-Up Networks. CVPR, 2021. [Code]

Multi-View Multi-Person 3D Pose Estimation with Plane Sweep Stereo. CVPR, 2021. [Code]

PCLs: Geometry-aware Neural Reconstruction of 3D Pose with Perspective Crop Layers. CVPR, 2021.

PoseAug: A Differentiable Pose Augmentation Framework for 3D Human Pose Estimation. CVPR (Oral), 2021. [Page] [Code]

Camera Distortion-aware 3D Human Pose Estimation in Video with Optimization-based Meta-Learning. ICCV, 2021. [Code]

Learning Skeletal Graph Neural Networks for Hard 3D Pose Estimation. ICCV, 2021. [Code]

Probabilistic Monocular 3D Human Pose Estimation with Normalizing Flows. ICCV, 2021. [Code]

Direct Multi-view Multi-person 3D Human Pose Estimation. NeurIPS, 2021. [Code]

Neural Monocular 3D Human Motion Capture with Physical Awareness. SIGGRAPH, 2021. [Page] [Code]

Learning Dynamical Human-Joint Affinity for 3D Pose Estimation in Videos. TIP, 2021.

Fast and Robust Multi-Person 3D Pose Estimation from Multiple Views. TPAMI, 2021. [Page] [Code]

PI-Net: Pose Interacting Network for Multi-Person Monocular 3D Pose Estimation. WACV, 2021.

2022

Neural MoCon: Neural Motion Control for Physically Plausible Human Motion Capture. CVPR, 2022. [Page]

Naked Body Mesh

Before 2018

Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image. ECCV, 2016. [Page] [Code]

2018

Neural Body Fitting: Unifying Deep Learning and Model Based Human Pose and Shape Estimation. 3DV (Oral), 2018. [Code]

End-to-end Recovery of Human Shape and Pose. CVPR, 2018. [Page] [Code]

Learning to Estimate 3D Human Pose and Shape from a Single Color Image. CVPR, 2018. [Page]

Total Capture: A 3D Deformation Model for Tracking Faces, Hands, and Bodies. CVPR (Oral), 2018. [Page]

2019

Learning 3D Human Shape and Pose from Dense Body Parts. ArXiv, 2019. [Page] [Code]

Expressive Body Capture: 3D Hands, Face, and Body from a Single Image. CVPR, 2019. [Page] [Code]

Learning 3D Human Dynamics from Video. CVPR, 2019. [Page] [Code]

Monocular Total Capture: Posing Face, Body and Hands in the Wild. CVPR (Oral), 2019. [Page] [Code]

Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Image. ICCV, 2019. [Code]

Delving Deep Into Hybrid Annotations for 3D Human Recovery in the Wild. ICCV, 2019. [Page] [Code]

Human Mesh Recovery from Monocular Images via a Skeleton-disentangled Representation. ICCV, 2019. [Code]

Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loop. ICCV, 2019. [Page] [Code]

2020

PoseNet3D: Learning Temporally Consistent 3D Human Pose via Knowledge Distillation. 3DV, 2020.

3D Human Motion Estimation via Motion Compression and Refinement. ACCV (Oral), 2020. [Page] [Code]

Parametric Shape Estimation of Human Body under Wide Clothing. ACM MM, 2020. [Code]

Beyond Weak Perspective for Monocular 3D Human Pose Estimation. ArXiv, 2020.

CenterHMR: a Bottom-up Single-shot Method for Multi-person 3D Mesh Recovery from a Single Image. ArXiv, 2020. [Code]

Chasing the Tail in Monocular 3D Human Reconstruction with Prototype Memory. ArXiv, 2020.

Exemplar Fine-Tuning for 3D Human Pose Fitting Towards In-the-Wild 3D Human Pose Estimation. ArXiv, 2020. [Code]

FrankMocap: A Fast Monocular 3D Hand and Body Motion Capture by Regression and Integration. ArXiv, 2020. [Page] [Code]

Human Mesh Recovery from Multiple Shots. ArXiv, 2020. [Page]

Monocular, One-stage, Regression of Multiple 3D People. ArXiv, 2020. [Code]

NeuralAnnot: Neural Annotator for in-the-wild Expressive 3D Human Pose and Mesh Training Sets. ArXiv, 2020. [Page]

Pose2Pose: 3D Positional Pose-Guided 3D Rotational Pose Prediction for Expressive 3D Human Pose and Mesh Estimation. ArXiv, 2020. [Page]

Full-body motion capture for multiple closely interacting persons. CVM, 2020.

3D Human Mesh Regression with Dense Correspondence. CVPR, 2020. [Code]

Coherent Reconstruction of Multiple Humans from a Single Image. CVPR, 2020. [Page] [Code]

Object-Occluded Human Shape and Pose Estimation from a Single Color Image. CVPR, 2020. [Page] [Code]

VIBE: Video Inference for Human Body Pose and Shape Estimation. CVPR, 2020. [Code]

Full-Body Awareness from Partial Observations. ECCV, 2020. [Page] [Code]

Hierarchical Kinematic Human Mesh Recovery. ECCV, 2020. [Page]

Human Body Model Fitting by Learned Gradient Descent. ECCV, 2020. [Page]

I2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB Image. ECCV, 2020. [Code]

Monocular Expressive Body Regression through Body-Driven Attention. ECCV, 2020. [Page] [Code]

Pose2Mesh: Graph Convolutional Network for 3D Human Pose and Mesh Recovery from a 2D Human Pose. ECCV, 2020. [Code]

Appearance Consensus Driven Self-Supervised Human Mesh Recovery. ECCV (Oral), 2020. [Page] [Code]

3D Multi-bodies: Fitting Sets of Plausible 3D Human Models to Ambiguous Image Data. NeurIPS, 2020.

MeshLifter: Weakly Supervised Approach for 3D Human Mesh Reconstruction from a Single 2D Pose Based on Loop Structure. Sensors, 2020. [Code]

Learning 3D Human Shape and Pose from Dense Body Parts. TPAMI, 2020. [Page] [Code]

2021

PC-HMR: Pose Calibration for 3D Human Mesh Recovery from 2D Images/Videos. AAAI, 2021.

3D Human Pose, Shape and Texture from Low-Resolution Images and Videos. ArXiv, 2021.

A Lightweight Graph Transformer Network for Human Mesh Reconstruction from 2D Human Pose. ArXiv, 2021.

Collaborative Regression of Expressive Bodies using Moderation. ArXiv, 2021. [Page]

Everybody Is Unique: Towards Unbiased Human Mesh Recovery. ArXiv, 2021.

Heuristic Weakly Supervised 3D Human Pose Estimation in Novel Contexts without Any 3D Pose Ground Truth. ArXiv, 2021.

KAMA: 3D Keypoint Aware Body Mesh Articulation. ArXiv, 2021.

Learning Local Recurrent Models for Human Mesh Recovery. ArXiv, 2021.

PARE: Part Attention Regressor for 3D Human Body Estimation. ArXiv, 2021. [Page]

Revitalizing Optimization for 3D Human Pose and Shape Estimation: A Sparse Constrained Formulation. ArXiv, 2021.

Self-Attentive 3D Human Pose and Shape Estimation from Videos. ArXiv, 2021.

THUNDR: Transformer-based 3D HUmaN Reconstruction with Markers. ArXiv, 2021.

Beyond Static Features for Temporally Consistent 3D Human Pose and Shape from a Video. CVPR, 2021. [Page] [Code]

Bilevel Online Adaptation for Out-of-Domain Human Mesh Reconstruction. CVPR, 2021. [Page] [Code]

Body Meshes as Points. CVPR, 2021. [Page] [Code]

End-to-End Human Pose and Mesh Reconstruction with Transformers. CVPR, 2021. [Code]

HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimation. CVPR, 2021. [Page] [Code]

Monocular Real-time Full Body Capture with Inter-part Correlations. CVPR, 2021. [Page]

On Self-Contact and Human Pose. CVPR, 2021. [Page]

Out-of-Domain Human Mesh Reconstruction via Bilevel Online Adaptation. CVPR, 2021. [Page] [Code]

Probabilistic 3D Human Shape and Pose Estimation from Multiple Unconstrained Images in the Wild. CVPR, 2021.

Reconstructing 3D Human Pose by Watching Humans in the Mirror. CVPR (Oral), 2021. [Page] [Code]

SimPoE: Simulated Character Control for 3D Human Pose Estimation. CVPR (Oral), 2021. [Page]

Encoder-decoder with Multi-level Attention for 3D Human Shape and Pose Estimation. ICCV, 2021. [Code]

Hierarchical Kinematic Probability Distributions for 3D Human Shape and Pose Estimation from Images in the Wild. ICCV, 2021. [Code]

HuMoR: 3D Human Motion Model for Robust Pose Estimation. ICCV, 2021. [Page]

Learning to Regress Bodies from Images using Differentiable Semantic Rendering. ICCV, 2021. [Page]

Lightweight Multi-person Total Motion Capture Using Sparse Multi-view Cameras. ICCV, 2021. [Page]

Physics-based Human Motion Estimation and Synthesis from Videos. ICCV, 2021.

Probabilistic Modeling for Human Mesh Recovery. ICCV, 2021. [Page] [Code]

SOMA: Solving Optical Marker-Based MoCap Automatically. ICCV, 2021. [Page]

Shape-aware Multi-Person Pose Estimation from Multi-View Images. ICCV, 2021. [Page] [Code]

PyMAF: 3D Human Pose and Shape Regression with Pyramidal Mesh Alignment Feedback Loop. ICCV (Oral), 2021. [Page] [Code]

SportsCap: Monocular 3D Human Motion Capture and Fine-grained Understanding in Challenging Sports Videos. IJCV, 2021. [Page] [Code]

TransPose: Real-time 3D Human Translation and Pose Estimation with Six Inertial Sensors. SIGGRAPH, 2021. [Page] [Code]

Real-time RGBD-based Extended Body Pose Estimation. WACV, 2021. [Code]

2022

Capturing Humans in Motion: Temporal-Attentive 3D Human Pose and Shape Estimation from Monocular Video. CVPR, 2022. [Page] [Code]

LiDARCap: Long-range Marker-less 3D Human Motion Capture with LiDAR Point Clouds. CVPR, 2022.

Occluded Human Mesh Recovery. CVPR, 2022. [Page]

Physical Inertial Poser (PIP): Physics-aware Real-time Human Motion Tracking from Sparse Inertial Sensors. CVPR, 2022. [Page] [Code]

Putting People in their Place: Monocular Regression of 3D People in Depth. CVPR, 2022. [Page] [Code]

GLAMR: Global Occlusion-Aware Human Mesh Recovery with Dynamic Cameras. CVPR (Oral), 2022. [Page] [Code]

FastMETRO: Cross-Attention of Disentangled Modalities for 3D Human Mesh Recovery with Transformers. ECCV, 2022. [Page] [Code]

Out-of-Domain Human Mesh Reconstruction via Dynamic Bilevel Online Adaptation. TPAMI, 2022. [Page] [Code]

2023

Binarized 3D Whole-body Human Mesh Recovery. ArXiv, 2023. [Code]

Implicit 3D Human Mesh Recovery using Consistency with Pose and Shape from Unseen-view. CVPR, 2023.

One-Stage 3D Whole-Body Mesh Recovery. CVPR, 2023. [Page] [Code]

TRACE: 5D Temporal Regression of Avatars with Dynamic Cameras in 3D Environments. CVPR, 2023. [Page] [Code]

Scene-Aware 3D Multi-Human Motion Capture. Eurographics, 2023. [Page] [Code]

Generative Approach for Probabilistic Human Mesh Recovery using Diffusion Models. ICCV, 2023. [Code]

Video Inference for Human Mesh Recovery with Vision Transformer. IEEE Face and Gesture, 2023.

Clothed Body Mesh

Before 2018

Fast Generation of Realistic Virtual Humans. VRST, 2017. [Page]

2018

Detailed Human Avatars from Monocular Video. 3DV, 2018. [Code]

Video Based Reconstruction of 3D People Models. CVPR, 2018. [Page]

DoubleFusion: Real-time Capture of Human Performance with Inner Body Shape from a Depth Sensor. CVPR (Oral), 2018. [Page] [Code]

2019

Learning to Reconstruct People in Clothing from a Single RGB Camera. CVPR, 2019. [Page] [Code]

SiCloPe: Silhouette-Based Clothed People. CVPR, 2019.

SimulCap : Single-View Human Performance Capture with Cloth Simulation. CVPR, 2019. [Page]

3DPeople: Modeling the Geometry of Dressed Humans. ICCV, 2019. [Page] [Code]

Multi-Garment Net: Learning to Dress 3D People from Images. ICCV, 2019. [Page]

PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization. ICCV, 2019. [Page] [Code]

Tex2Shape: Detailed Full Human Body Geometry from a Single Image. ICCV, 2019. [Page] [Code]

LiveCap: Real-time Human Performance Capture from Monocular Video. SIGGRAPH, 2019. [Page]

3D Human Avatar Digitization from a Single Image. VRCAI, 2019.

2020

MonoClothCap: Towards Temporally Coherent Clothing Capture from Monocular RGB Video. 3DV, 2020.

Deep Physics-aware Inference of Cloth Deformation for Monocular Human Performance Capture. ArXiv, 2020.

RIN: Textured Human Model Recovery and Imitation with a Single Image. ArXiv, 2020.

ARCH: Animatable Reconstruction of Clothed Humans. CVPR, 2020.

Implicit Functions in Feature Space for 3D Shape Reconstruction and Completion. CVPR, 2020. [Page] [Code]

DeepCap: Monocular Human Performance Capture Using Weak Supervision. CVPR (Oral), 2020. [Page]

PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization. CVPR (Oral), 2020. [Page] [Code]

Robust 3D Self-portraits in Seconds. CVPR (Oral), 2020. [Page]

Monocular Real-Time Volumetric Performance Capture. ECCV, 2020. [Page] [Code]

NormalGAN: Learning Detailed 3D Human from a Single RGB-D Image. ECCV, 2020. [Page]

Reconstructing NBA Players. ECCV, 2020. [Page] [Code]

RobustFusion: Human Volumetric Capture with Data-driven Visual Cues using a RGBD Camera. ECCV, 2020.

TexMesh: Reconstructing Detailed Human Texture and Geometry from RGB-D Video. ECCV, 2020. [Page]

Combining Implicit Function Learning and Parametric Models for 3D Human Reconstruction. ECCV (Oral), 2020. [Page] [Code]

SIZER: A Dataset and Model for Parsing 3D Clothing and Learning Size Sensitive 3D Clothing. ECCV (Oral), 2020. [Page] [Code]

Geo-PIFu: Geometry and Pixel Aligned Implicit Functions for Single-view Human Reconstruction. NeurIPS, 2020. [Code]

PaMIR: Parametric Model-Conditioned Implicit Representation for Image-based Human Reconstruction. TPAMI, 2020. [Page]

MulayCap: Multi-layer Human Performance Capture Using A Monocular Video Camera. TVCG, 2020. [Page]

Realistic Virtual Humans from Smartphone Videos. VRST, 2020. [Page]

2021

Human Performance Capture from Monocular Video in the Wild. 3DV, 2021. [Page] [Code]

Capturing Detailed Deformations of Moving Human Bodies. ArXiv, 2021.

DSFN: Dynamic Surface Function Networks for Clothed Human Bodies. ArXiv, 2021. [Page] [Code]

DeepMultiCap: Performance Capture of Multiple Characters Using Sparse Multiview Cameras. ArXiv, 2021. [Page]

Total Scale: Face-to-Body Detail Reconstruction from Sparse RGBD Sensors. ArXiv, 2021.

ChallenCap: Monocular 3D Capture of Challenging Human Performances using Multi-Modal References. CVPR, 2021.

S3: Neural Shape, Skeleton, and Skinning Fields for 3D Human Modeling. CVPR, 2021.

SMPLicit: Topology-aware Generative Model for Clothed People. CVPR, 2021. [Page] [Code]

StereoPIFu: Depth Aware Clothed Human Digitization via Stereo Vision. CVPR, 2021. [Page] [Code]

Towards Real-World Category-level Articulation Pose Estimation. CVPR, 2021. [Page]

Function4D: Real-time Human Volumetric Capture from Very Sparse Consumer RGBD Sensors. CVPR (Oral), 2021. [Page]

Neural Deformation Graphs for Globally-consistent Non-rigid Reconstruction. CVPR (Oral), 2021. [Page]

POSEFusion:Pose-guided Selective Fusion for Single-view Human Volumetric Capture. CVPR (Oral), 2021. [Page]

SCANimate: Weakly Supervised Learning of Skinned Clothed Avatar Networks. CVPR (Oral), 2021. [Page] [Code]

ARCH++: Animation-Ready Clothed Human Reconstruction Revisited. ICCV, 2021.

Neural-GIF: Neural Generalized Implicit Functions for Animating People in Clothing. ICCV, 2021. [Page]

Image-Guided Human Reconstruction via Multi-Scale Graph Transformation Networks. TIP, 2021. [Page] [Code]

Detailed Avatar Recovery from Single Image. TPAMI, 2021.

TightCap: 3D Human Shape Capture with Clothing Tightness Field. ToG, 2021. [Page] [Code]

2022

ReFu: Refine and Fuse the Unobserved View for Detail-Preserving Single-Image 3D Human Reconstruction. ACM MM, 2022.

HDHumans: A Hybrid Approach for High-fidelity Digital Humans. ArXiv, 2022.

PatchShading: High-Quality Human Reconstruction by PatchWarping and Shading Refinement. ArXiv, 2022.

gDNA: Towards Generative Detailed Neural Avatars. ArXiv, 2022. [Page]

High-Fidelity Human Avatars from a Single RGB Camera. CVPR, 2022. [Page] [Code]

ICON: Implicit Clothed humans Obtained from Normals. CVPR, 2022. [Page] [Code]

OcclusionFusion: Occlusion-aware Motion Estimation for Real-time Dynamic 3D Reconstruction. CVPR, 2022. [Page] [Code]

PINA: Learning a Personalized Implicit Neural Avatar from a Single RGB-D Video Sequence. CVPR, 2022. [Page] [Code]

SelfRecon: Self Reconstruction Your Digital Avatar from Monocular Video. CVPR (Oral), 2022. [Page] [Code]

AvatarCap: Animatable Avatar Conditioned Monocular Human Volumetric Capture. ECCV, 2022. [Page] [Code]

Geometry-aware Two-scale PIFu Representation for Human Reconstruction. NeurIPS, 2022.

TotalSelfScan: Learning Full-body Avatars from Self-Portrait Videos of Faces, Hands, and Bodies. NeurIPS, 2022.

Capturing and Animation of Body and Clothing from Monocular Video. SIGGRAPH Asia, 2022. [Page] [Code]

2023

ECON: Explicit Clothed humans Optimized via Normal integration. CVPR, 2023. [Page] [Code]

High-Fidelity Clothed Avatar Reconstruction from a Single Image. CVPR, 2023. [Page] [Code]

Human Depth Estimation

2019

Learning the Depths of Moving People by Watching Frozen People. CVPR, 2019. [Page] [Code]

A Neural Network for Detailed Human Depth Estimation from a Single Image. ICCV, 2019. [Code]

2020

Self-Supervised Human Depth Estimation from Monocular Videos. CVPR, 2020. [Code]

2021

DressNet: High Fidelity Depth Estimation of Dressed Humans from a Single View Image. ArXiv, 2021.

Boosting Monocular Depth Estimation Models to High-Resolution via Content-Adaptive Multi-Resolution Merging. CVPR, 2021. [Page] [Code]

Learning High Fidelity Depths of Dressed Humans by Watching Social Media Dance Videos. CVPR (Oral), 2021. [Page] [Code]

Human Motion

2018

3D Semantic Trajectory Reconstruction from 3D Pixel Continuum. CVPR, 2018. [Page]

2019

Predicting 3D Human Dynamics from Video. ICCV, 2019. [Page] [Code]

2020

Convolutional Autoencoders for Human Motion Infilling. 3DV, 2020.

Adversarial Refinement Network for Human Motion Prediction. ACCV, 2020.

Long-term Human Motion Prediction with Scene Context. ECCV (Oral), 2020. [Page] [Code]

Robust Motion In-betweening. SIGGRAPH, 2020. [Page]

Character Controllers using Motion VAEs. ToG, 2020. [Page] [Code]

2021

Aggregated Multi-GANs for Controlled 3D Human Motion Prediction. AAAI, 2021. [Code]

A Causal Convolutional Neural Network for Motion Modeling and Synthesis. ArXiv, 2021.

Action-Conditioned 3D Human Motion Synthesis with Transformer VAE. ArXiv, 2021. [Page]

DanceNet3D: Music Based Dance Generation with Parametric Motion Transformer. ArXiv, 2021. [Page] [Code]

Flow-based Autoregressive Structured Prediction of Human Motion. ArXiv, 2021.

Improving Human Motion Prediction Through Continual Learning. ArXiv, 2021.

Learn to Dance with AIST++: Music Conditioned 3D Dance Generation. ArXiv, 2021. [Page]

Learning Speech-driven 3D Conversational Gestures from Video. ArXiv, 2021.

Multi-level Motion Attention for Human Motion Prediction. ArXiv, 2021. [Code]

Rhythm is a Dancer: Music-Driven Motion Synthesis with Global Structure. ArXiv, 2021.

Single-Shot Motion Completion with Transformer. ArXiv, 2021. [Code]

TRiPOD: Human Trajectory and Pose Dynamics Forecasting in the Wild. ArXiv, 2021. [Page]

Task-Generic Hierarchical Human Motion Prior using VAEs. ArXiv, 2021.

TrajeVAE - Controllable Human Motion Generation from Trajectories. ArXiv, 2021. [Page]

Scene-aware Generative Network for Human Motion Synthesis. CVPR, 2021.

Synthesizing Long-Term 3D Human Motion and Interaction in 3D. CVPR, 2021. [Page] [Code]

Towards Accurate 3D Human Motion Prediction from Incomplete Observations. CVPR, 2021.

We are More than Our Joints: Predicting how 3D Bodies Move. CVPR, 2021. [Page]

Learning Compositional Representation for 4D Captures with Neural ODE. CVPR (Oral), 2021. [Page] [Code]

Graph Constrained Data Representation Learning for Human Motion Segmentation. ICCV, 2021.

MSR-GCN: Multi-Scale Residual Graph Convolution Networks for Human Motion Prediction. ICCV, 2021. [Code]

Pose Transformers (POTR): Human Motion Prediction with Non-Autoregressive Transformers. ICCV, 2021. [Code]

Stochastic Scene-Aware Motion Prediction. ICCV, 2021. [Page] [Code]

Skeleton-Graph: Long-Term 3D Motion Prediction From 2D Observations Using Deep Spatio-Temporal Graph CNNs. ICCV (Workshop), 2021. [Code]

GlocalNet: Class-aware Long-term Human Motion Synthesis. MACV, 2021.

Multi-Person 3D Motion Prediction with Multi-Range Transformers. NeurIPS, 2021. [Page]

Tracking People with 3D Representations. NeurIPS, 2021. [Page] [Code]

Learning a Family of Motor Skills from a Single Motion Clip. SIGGRAPH, 2021. [Page] [Code]

Multiscale Spatio-Temporal Graph Neural Networks for 3D Skeleton-Based Motion Prediction. TIP, 2021.

2022

BeLFusion: Latent Diffusion for Behavior-Driven Human Motion Prediction. ArXiv, 2022. [Page] [Code]

DualMotion: Global-to-Local Casual Motion Design for Character Animations. ArXiv, 2022.

GIMO: Gaze-Informed Human Motion Prediction in Context. ArXiv, 2022.

Bailando: 3D Dance Generation by Actor-Critic GPT with Choreographic Memory. CVPR, 2022. [Code]

Tracking People by Predicting 3D Appearance, Location and Pose. CVPR, 2022. [Page] [Code]

MUGL: Large Scale Multi Person Conditional Action Generation with Locomotion. WACV, 2022. [Page] [Code]

2023

DanceAnyWay: Synthesizing Mixed-Genre 3D Dance Movements Through Beat Disentanglement. ArXiv, 2023.

Human-Object Interaction

2019

Resolving 3D Human Pose Ambiguities with 3D Scene Constraints. ICCV, 2019. [Page] [Code]

2020

GRAB: A Dataset of Whole-Body Human Grasping of Objects. ECCV, 2020. [Page] [Code]

Perceiving 3D Human-Object Spatial Arrangements from a Single Image in the Wild. ECCV, 2020. [Page] [Code]

2021

Holistic 3D Human and Scene Mesh Estimation from Single View Images. CVPR, 2021.

Human POSEitioning System (HPS): 3D Human Pose Estimation and Self-localization in Large Scenes from Body-Mounted Sensors. CVPR, 2021. [Page]

Populating 3D Scenes by Learning Human-Scene Interaction. CVPR, 2021. [Page] [Code]

Soft Walks: Real-Time, Two-Ways Interaction between a Character and Loose Grounds. Eurographics, 2021.

Gravity-Aware Monocular 3D Human-Object Reconstruction. ICCV, 2021. [Page] [Code]

RobustFusion: Robust Volumetric Performance Reconstruction under Human-object Interactions from Monocular RGBD Stream. TPAMI, 2021.

2022

FLEX: Full-Body Grasping Without Full-Body Grasps. ArXiv, 2022. [Page] [Code]

BEHAVE: Dataset and Method for Tracking Human Object Interactions. CVPR, 2022. [Page] [Code]

CHORE: Contact, Human and Object REconstruction from a single RGB image. ECCV, 2022. [Page] [Code]

InterCap: Joint Markerless 3D Tracking of Humans and Objects in Interaction. GCPR, 2022. [Page] [Code]

Animation

2019

Predicting Animation Skeletons for 3D Articulated Models via Volumetric Nets. 3DV (Oral), 2019. [Page] [Code]

2020

DeePSD: Automatic Deep Skinning And Pose Space Deformation For 3D Garment Animation. ArXiv, 2020.

UniCon: Universal Neural Controller For Physics-based Character Motion. ArXiv, 2020. [Page]

Functionality-Driven Musculature Retargeting. CGF, 2020. [Page] [Code]

Motion Retargetting based on Dilated Convolutions and Skeleton-specific Loss Functions. Eurographics, 2020. [Page] [Code]

RigNet: Neural Rigging for Articulated Characters. SIGGRAPH, 2020. [Page] [Code]

Skeleton-Aware Networks for Deep Motion Retargeting. SIGGRAPH, 2020. [Page] [Code]

2021

Temporal Parameter-free Deep Skinning of Animated Meshes. CGI, 2021. [Page]

Flow Guided Transformable Bottleneck Networks for Motion Retargeting. CVPR, 2021.

A Deep Emulator for Secondary Motion of 3D Characters. CVPR (Oral), 2021. [Page]

HeterSkinNet: A Heterogeneous Network for Skin Weights Prediction. I3D, 2021.

Contact-Aware Retargeting of Skinned Motion. ICCV, 2021.

Learning Skeletal Articulations With Neural Blend Shapes. SIGGRAPH, 2021. [Page] [Code]

Cloth/Try-On

2018

DeepWrinkles: Accurate and Realistic Clothing Modeling. ECCV (Oral), 2018.

2019

Learning-Based Animation of Clothing for Virtual Try-On. Eurographics, 2019. [Page] [Code]

Wallpaper Pattern Alignment along Garment Seams. SIGGRAPH, 2019. [Page]

Reflection Symmetry in Textured Sewing Patterns. VMV, 2019. [Page]

2020

DeepCloth: Neural Garment Representation for Shape and Style Editing. ArXiv, 2020. [Page]

Physically Based Neural Simulator for Garment Animation. ArXiv, 2020.

SNUG: Self-Supervised Neural Dynamic Garments. CVPR (Oral), 2020. [Page] [Code]

TailorNet: Predicting Clothing in 3D as a Function of Human Pose, Shape and Garment Style. CVPR (Oral), 2020. [Page] [Code]

BCNet: Learning Body and Cloth Shape from a Single Image. ECCV, 2020. [Code]

Deep Fashion3D: A Dataset and Benchmark for 3D Garment Reconstruction from Single-view Images. ECCV (Oral), 2020. [Page]

Fully Convolutional Graph Neural Networks for Parametric Virtual Try-On. SCA, 2020. [Page]

P-Cloth: Interactive Complex Cloth Simulation on Multi-GPU Systems using Dynamic Matrix Assembly and Pipelined Implicit Integrators. SIGGRAPH Asia, 2020. [Page] [Code]

2021

3D Custom Fit Garment Design with Body Movement. ArXiv, 2021.

Deep Deformation Detail Synthesis for Thin Shell Models. ArXiv, 2021.

Detail-aware Deep Clothing Animations Infused with Multi-source Attributes. ArXiv, 2021.

DiffCloth: Differentiable Cloth Simulation with Dry Frictional Contact. ArXiv, 2021.

Example-based Real-time Clothing Synthesis for Virtual Agents. ArXiv, 2021.

Neural 3D Clothes Retargeting from a Single Image. ArXiv, 2021.

Robust 3D Garment Digitization from Monocular 2D Images for 3D Virtual Try-On Systems. ArXiv, 2021.

Self-Supervised Collision Handling via Generative 3D Garment Models for Virtual Try-On. CVPR, 2021. [Page]

Garment4D: Garment Reconstruction from Point Cloud Sequences. NeurIPS, 2021. [Page] [Code]

Dynamic Neural Garments. SIGGRAPH Asia, 2021. [Page] [Code]

2022

DIG: Draping Implicit Garment over the Human Body. ACCV, 2022. [Page] [Code]

Registering Explicit to Implicit: Towards High-Fidelity Garment Mesh Reconstruction from Single Images. CVPR, 2022. [Page] [Code]

3D Clothed Human Reconstruction in the Wild. ECCV, 2022. [Code]

N-Cloth: Predicting 3D Cloth Deformation with Mesh-Based Networks. Eurographics, 2022. [Page]

ULNeF: Untangled Layered Neural Fields for Mix-and-Match Virtual Try-On. NeurIPS, 2022. [Page]

PERGAMO: Personalized 3D Garments from Monocular Video. SCA, 2022. [Page] [Code]

Motion Guided Deep Dynamic 3D Garments. SIGGRAPH Asia, 2022. [Page] [Code]

Neural Cloth Simulation. SIGGRAPH Asia, 2022. [Page] [Code]

2023

REC-MV: REconstructing 3D Dynamic Cloth from Monocular Videos. CVPR, 2023. [Page] [Code]

Neural Rendering

2020

Neural3D: Light-weight Neural Portrait Scanning via Context-aware Correspondence Learning. ACM MM, 2020.

ANR: Articulated Neural Rendering for Virtual Avatars. ArXiv, 2020. [Page]

Vid2Actor: Free-viewpoint Animatable Person Synthesis from Video in the Wild. ArXiv, 2020. [Page]

Multi-view Neural Human Rendering. CVPR, 2020. [Page] [Code]

Rotationally-Temporally Consistent Novel-View Synthesis of Human Performance Video. ECCV, 2020. [Code]

SMPLpix: Neural Avatars from 3D Human Models. WACV, 2020. [Page] [Code]

2021

A-NeRF: Surface-free Human 3D Pose Refinement via Neural Rendering. ArXiv, 2021. [Page]

Animatable Neural Radiance Fields for Human Body Modeling. ArXiv, 2021. [Page] [Code]

Efficient Neural Radiance Fields with Learned Depth-Guided Sampling. ArXiv, 2021. [Page]

Few-shot Neural Human Performance Rendering from Sparse RGBD Videos. ArXiv, 2021.

Human View Synthesis using a Single Sparse RGB-D Input. ArXiv, 2021. [Page]

LookinGood^π: Real-time Person-independent Neural Re-rendering for High-quality Human Performance Capture. ArXiv, 2021.

MoCo-Flow: Neural Motion Consensus Flow for Dynamic Humans in Stationary Monocular Cameras. ArXiv, 2021.

Neural Actor: Neural Free-view Synthesis of Human Actors with Pose Control. ArXiv, 2021.

Neural Articulated Radiance Field. ArXiv, 2021. [Code]

Neural Free-Viewpoint Performance Rendering under Complex Human-object Interactions. ArXiv, 2021.

Neural Human Performer: Learning Generalizable Radiance Fields for Human Performance Rendering. ArXiv, 2021. [Page]

D-NeRF: Neural Radiance Fields for Dynamic Scenes. CVPR, 2021. [Page]

Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humans. CVPR, 2021. [Page] [Code]

NeuralHumanFVV: Real-Time Neural Volumetric Human Performance Rendering using RGB Cameras. CVPR, 2021.

StylePeople: A Generative Model of Fullbody Human Avatars. CVPR, 2021. [Page] [Code]

Animatable Neural Implicit Surfaces for Creating Avatars from Videos. ICCV, 2021. [Page] [Code]

Editable Free-viewpoint Video Using a Layered Neural Representation. SIGGRAPH, 2021. [Page]

2022

Dual-Space NeRF: Learning Animatable Avatars and Scene Lighting in Separate Spaces. 3DV, 2022.

HumanNeRF: Free-viewpoint Rendering of Moving People from Monocular Video. ArXiv, 2022. [Page]

InstantAvatar: Learning Avatars from Monocular Video in 60 Seconds. ArXiv, 2022. [Page] [Code]

RANA: Relightable Articulated Neural Avatars. ArXiv, 2022. [Page]

UV Volumes for Real-time Rendering of Editable Free-view Human Performance. ArXiv, 2022. [Page] [Code]

DoubleField: Bridging the Neural Surface and Radiance Fields for High-fidelity Human Reconstruction and Rendering. CVPR, 2022. [Page]

HumanNeRF: Generalizable Neural Human Radiance Field from Sparse Inputs. CVPR, 2022. [Page] [Code]

Structured Local Radiance Fields for Human Avatar Modeling. CVPR, 2022. [Page]

NeuMan: Neural Human Radiance Field from a Single Video. ECCV, 2022. [Code]

Human Performance Modeling and Rendering via Neural Animated Mesh. SIGGRAPH Asia, 2022. [Page] [Code]

Dataset

2018

3DBodyTex: Textured 3D Body Dataset. 3DV, 2018. [Page]

3DPW: Recovering Accurate 3D Human Pose in The Wild Using IMUs and a Moving Camera. ECCV, 2018. [Page]

2019

3DPeople: Modeling the Geometry of Dressed Humans. ICCV, 2019. [Page] [Code]

AMASS: Archive of Motion Capture as Surface Shapes. ICCV, 2019. [Page] [Code]

2020

SMPLy Benchmarking 3D Human Pose Estimation in the Wild. 3DV (Oral), 2020. [Page]

HUMBI: A Large Multiview Dataset of Human Body Expressions. CVPR, 2020. [Page] [Code]

Object-Occluded Human Shape and Pose Estimation from a Single Color Image. CVPR, 2020. [Page] [Code]

Full-Body Awareness from Partial Observations. ECCV, 2020. [Page] [Code]

Motion Capture from Internet Videos. ECCV (Oral), 2020. [Page] [Code]

2021

AGORA: Avatars in Geography Optimized for Regression Analysis. CVPR, 2021. [Page]

BABEL: Bodies, Action and Behavior with English Labels. CVPR, 2021. [Page]

Reconstructing 3D Human Pose by Watching Humans in the Mirror. CVPR (Oral), 2021. [Page] [Code]

2022

BEHAVE: Dataset and Method for Tracking Human Object Interactions. CVPR, 2022. [Page] [Code]

HuMMan: Multi-Modal 4D Human Dataset for Versatile Sensing and Modeling. ECCV (Oral), 2022. [Page]