Shuolin's repositories
HRNet-combine-CBAM-f-Cephalometric-Landmark-Detection
Topdown Heatmap regression based HRNet combine CBAM for Cephalometric Landmark Detection in Lateral X-ray Images
deep-motion-editing
An end-to-end library for editing and rendering motion of 3D characters with deep learning [SIGGRAPH 2020]
human_dynamics
Project for paper "Learning 3D Human Dynamics from Video"
MeshTransformer
Research code for CVPR 2021 paper "End-to-End Human Pose and Mesh Reconstruction with Transformers"
motion_puzzle
Motion Puzzle - Official PyTorch implementation
randomCropper
Crop large images randomly, where objects are inside the box.
supr_convertor
A simple tool to convert SMPL-X model parameters to SUPR model parameters
velocity_skinning_cpp
Implementation of the Velocity Skinning algorithm in C++
AS-project
image recog project use cnn
Auto-GPT
An experimental open-source attempt to make GPT-4 fully autonomous.
BiFormer
[CVPR 2023] Official code release of our paper "BiFormer: Vision Transformer with Bi-Level Routing Attention"
CVPR2023-Papers-with-Code
CVPR 2023 论文和开源项目合集
FastMETRO
[ECCV'22] Official PyTorch Implementation of "Cross-Attention of Disentangled Modalities for 3D Human Mesh Recovery with Transformers"
learning_research
本人博士期间的科研经验
MotionBERT
PyTorch Implementation of "Learning Human Motion Representations: A Unified Perspective"
Online-Motion-Style-Transfer
Code for the CVPR 2022 Paper - Style-ERD: Responsive and Coherent Online Motion Style Transfer
Pose2Mesh_RELEASE
Official Pytorch implementation of "Pose2Mesh: Graph Convolutional Network for 3D Human Pose and Mesh Recovery from a 2D Human Pose", ECCV 2020
segment-anything
The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
skills-github-pages
My clone repository
SlicerTotalSegmentator
Fully automatic total body segmentation in 3D Slicer using "TotalSegmentator" AI model
smplx
SMPL-X
VIBE_XU_changed
Some additions, optimizations and modifications to the source code base based on the VIBE paper reproduction