tianyu06030020's repositories
3DMPPE_ROOTNET_RELEASE
Official PyTorch implementation of "Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Image", ICCV 2019
AirPose
This repository contains the code of AirPose, our multi-view fusion network for Human Pose and Shape Estimation method
Bailando
Code for CVPR 2022 paper "Bailando: 3D dance generation via Actor-Critic GPT with Choreographic Memory"
CPEM
PyTorch implementation of "Towards Accurate Facial Motion Retargeting with Identity-Consistent and Expression-Exclusive Constraints" (AAAI2022)
DeepFaceLive
Real-time face swap for PC streaming or video calls
DeepFly3D
Motion capture (markerless 3D pose estimation) pipeline and helper GUI for tethered Drosophila.
EasyMocap
Make human motion capture easier.
FastSpeech2
An implementation of Microsoft's "FastSpeech 2: Fast and High-Quality End-to-End Text to Speech"
frankmocap
A Strong and Easy-to-use Single View 3D Hand+Body Pose Estimator
human_body_prior
VPoser: Variational Human Pose Prior
HybrIK
Official code of "HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimation", CVPR 2021
LVD
Code for the paper Learned Vertex Descent: A New Direction for 3D Human Model Fitting (ECCV 2022)
minimal-hand
A minimal solution to hand motion capture from a single color camera at over 100fps. Easy to use, plug to run.
Minimal-IK
Solving SMPL/MANO parameters from keypoint coordinates.
MocapNET
We present MocapNET, a real-time method that estimates the 3D human pose directly in the popular Bio Vision Hierarchy (BVH) format, given estimations of the 2D body joints originating from monocular color images. Our contributions include: (a) A novel and compact 2D pose NSRM representation. (b) A human body orientation classifier and an ensemble of orientation-tuned neural networks that regress the 3D human pose by also allowing for the decomposition of the body to an upper and lower kinematic hierarchy. This permits the recovery of the human pose even in the case of significant occlusions. (c) An efficient Inverse Kinematics solver that refines the neural-network-based solution providing 3D human pose estimations that are consistent with the limb sizes of a target person (if known). All the above yield a 33% accuracy improvement on the Human 3.6 Million (H3.6M) dataset compared to the baseline method (MocapNET) while maintaining real-time performance
OpenSeeFace
Robust realtime face and facial landmark tracking on CPU with Unity integration
PaddleVideo
基于模块化的设计，提供丰富的视频算法实现、产业级的视频算法优化与应用，包括安防、体育、互联网、媒体等行业的动作定位与识别、行为分析、智能封面、视频标注、视频打标签等，涵盖动作识别与视频分类、动作定位、动作检测、多模态文本视频检索等技术。
PhysCap_demo_release
PhysCap: Physically Plausible Monocular 3D Motion Capture in Real Time The implementation is based on [SIGGRAPH Aisa'20](https://vcai.mpi-inf.mpg.de/projects/PhysCap/).
PoseTriplet
[CVPR 2022] PoseTriplet: Co-evolving 3D Human Pose Estimation, Imitation, and Hallucination under Self-supervision (Oral)
ROMP
Monocular, One-stage, Regression of Multiple 3D People, ROMP[ICCV21], BEV[CVPR22]
STTFormer
Spatio-Temporal Tuples Transformer for Skeleton-Based Action Recognition
StyleSpeech
Official implementation of Meta-StyleSpeech and StyleSpeech
Unified-Gesture-and-Fingertip-Detection
Unified learning approach for egocentric hand gesture recognition and fingertip detection.
VideoTo3dPoseAndBvh
Convert video to the bvh motion file
VT_with_NR_for_FER
Vision Transformer Equipped with Neural Resizer on Facial Expression Recognition Task, IEEE ICASSP 2022
XMem
[ECCV 2022] XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model
xrmocap
OpenXRLab Multi-view Motion Capture Toolbox and Benchmark