The record of paper reading

• Learning High Fidelity Depths of Dressed Humans by Watching Social Media Dance Videos

  

• PIFu_Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization

• Robust 3D Self-portraits in Seconds

• DeepCap_Monocular Human Performance Capture Using Weak Supervision

• SMPL: A Skinned Multi-Person Linear Model

• Mesh Graphormer

  

• Pose2Mesh: Graph Convolutional Networkfor 3D Human Pose and Mesh Recovery from a 2D Human Pose

  

• Convolutional Mesh Regression for Single-Image Human Shape Reconstruction

  

• HMR: End-to-end Recovery of Human Shape and Pose

  

• Human Body Model Fitting by Learned Gradient Descent

  

• Keypoint-aligned 3D Human Shape Recovery from A Single Image with Bilayer-Graph

  

• Skeleton2Mesh：Kinematics Prior Injected Unsupervised Human Mesh Recovery

  

• HKMR: Hierarchical Kinematic Human Mesh Recovery

  

• THUNDR: Transformer-based 3D HUmaN Reconstruction with Markers

  

• HoloPose: Holistic 3D Human Reconstruction In-The-Wild

  

• KAMA: 3D Keypoint Aware Body Mesh Articulation

  

• TUCH: On Self-Contact and Human Pose

  

• Shape as Points: A Differentiable Poisson Solver(roughly)

  

• Learning 3D Human Dynamics from Video

• VIBE: Video Inference for Human Body Pose and Shape Estimation

• TCMR: Beyond Static Features for Temporally Consistent 3D Human Pose and Shape from a Video

  

• MEVA: 3D Human Motion Estimation via Motion Compression and Refinement

  

• MPS-Net: Capturing Humans in Motion: Temporal-Attentive 3D Human Pose and Shape

  

• Uncertainty-Aware Human Mesh Recovery from Video by Learning Part-Based 3D Dynamics

  

• SRNet: Improving Generalization in 3D Human Pose Estimation with a Split-and-Recombine Approach

  

• Learning Skeletal Graph Neural Networks for Hard 3D Pose Estimation

  

• AlexNet: ImageNet Classifification with Deep Convolutional

  

• Transformer: Attention is All You Need

• SimAM: A Simple, Parameter-Free Attention Module for Convolutional Neural Networks

  

• UniFormer: Unified Transformer for Efficient Spatial-Temporal Representation Learning

  

• Learning Individually Inferred Communication for Multi-Agent Cooperation

• Emain：[email protected]