Bringing Characters to Life with Computer Brains in Unity

Extracts human motion in video and save it as bvh mocap file.

Unity sample of 3D pose estimation using Barracuda

Code to accompany "A Method for Animating Children's Drawings of the Human Figure"

BVH Tools for Unity

Matlab toolbox for Geometry Processing.

Simple MPL-2.0-licensed C++ geometry processing library.

Real-time pose estimation and action recognition

Apply ML to the skeletons from OpenPose; 9 actions; multiple people. (WARNING: I'm sorry that this is only good for course demo, not for real world applications !!! Those ary very difficult !!!)

A skeleton-based real-time online action recognition project, classifying and recognizing base on framewise joints, which can be used for safety surveilence.

Custom ava dataset, Multi-Person Video Dataset Annotation Method of Spatio-Temporally Actions

[CVPR 2023] 3D Cinemagraphy from a Single Image

Refine high-quality datasets and visual AI models

“Population-based Cooperative Gaming for Unsupervised Person Re-identification”, IJCV 2023.

"Multiple Expert Brainstorming for Domain Adaptive Person Re-identification", ECCV 2020

The code of our paper: Perceptual Video Coding for Machines via Satisfied Machine Ratio Modeling.

Yolov5+SlowFast: Realtime Action Detection Based on PytorchVideo

Desktop application to convert text-to-speech to preview Twitch donations.

Code for Motion Representations for Articulated Animation paper

[ICCV'21] Official implementation of the "Social NCE: Contrastive Learning of Socially-aware Motion Representations" in PyTorch, for Social-STGCNN on trajectory forecasting.

SwinGNN: diffusion model for graph generation

Accelerated SMPL operation, commonly used in generate 3D human mesh, STAR included.

This is an AI agent for Street Fighter II Champion Edition.

[ICCV2023] The PyTorch implementation for "Diffusion-Based 3D Human Pose Estimation with Multi-Hypothesis Aggregation"

[ICCV2023 Best Paper Finalist] PyTorch implementation of DiffusionDet (https://arxiv.org/abs/2211.09788)

Efficient 3D human pose estimation in video using 2D keypoint trajectories

北京大学出入校报备