Python-powered autorig for humanoid characters in Maya. Streamline full-body rigging with IK/FK blending, stretchy limbs, and customizable controls.

Python 3 implementation of FABRIK inverse kinematics algorithm.

Learning of Disentangled Pose and Movement for Unsupervised Motion Retargeting (BMVC 2019)

Single Image to 3D using Cross-Domain Diffusion for 3D Generation

This is an official implementation for "Contextual Transformer Networks for Visual Recognition".

Character Animation (AnimateAnyone, Face Reenactment)

Code of [CVPR 2024] "Semantics-aware Motion Retargeting with Vision-Language Models"

Unconditional Motion Synthesis from Diverse Data

Implementation of TimeSformer from Facebook AI, a pure attention-based solution for video classification

Implementation of STAM (Space Time Attention Model), a pure and simple attention model that reaches SOTA for video classification

The official pytorch implementation of our paper "Is Space-Time Attention All You Need for Video Understanding?"

从零编写游戏引擎教程 Writing a game engine tutorial from scratch

Interactive roadmaps, guides and other educational content to help developers grow in their careers.

Attention based Single Image Dehazing Using Improved CycleGAN

codes for paper "Pose-aware Attention Network for Flexible Motion Retargeting by Body Part" (TVCG2023)

An end-to-end library for editing and rendering motion of 3D characters with deep learning [SIGGRAPH 2020]

Convert video to the bvh motion file

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

Real-Time and Accurate Full-Body Multi-Person Pose Estimation&Tracking System

[ICCV 2023] PyTorch Implementation of "MotionBERT: A Unified Perspective on Learning Human Motion Representations"

[ECCV 2022] Official implementation of the paper "SmoothNet: A Plug-and-Play Network for Refining Human Poses in Videos"

[ECCV 2022] Official implementation of the paper "DeciWatch: A Simple Baseline for 10x Efficient 2D and 3D Pose Estimation"

Tensorflow implementation of the CVPR 2018 paper: Neural Kinematic Networks for Unsupervised Motion Retargetting

(CVPR 2023) Skinned Motion Retargeting with Residual Perception of Motion Semantics & Geometry

Reproduce the work of the paper "Skeleton-Aware Networks for Deep Motion Retargeting" in Pytorch

Motion Retargeting using RobOptim (EXPERIMENTAL)

PyTorch implementation for our paper Learning Character-Agnostic Motion for Motion Retargeting in 2D, SIGGRAPH 2019