skcskc7 Goto Github PK

3d_pose_baseline

3d_pose_baseline_pytorch

A simple baseline for 3d human pose estimation in PyTorch.

avatars4all

Live real-time avatars from your webcam in the browser. No dedicated hardware or software installation needed. A pure Google Colab wrapper for live First-order-motion-model, aka Avatarify in the browser. And other Colabs providing an accessible interface for using FOMM, Wav2Lip and Liquid-warping-GAN with your own media and a rich GUI.

awesome-text-to-3d

b3d_mocap_import

addon for blender to import mocap data from tools like easymocap, frankmocap and Vibe

blendarmocap

realtime motion tracking in blender using mediapipe and rigify

blendypose

Blender Motion Capture using your camera!

calibration-toolbox

Multiple-Camera System Calibration Toolbox for Matlab

curve-fitting-ransac

Curve fittings using Least Squares, Total Least Squares and RANSAC. Homography and Singular Value Decomposition

detailed-videoavatar

Reproduced Detailed-VideoAvatar project for 3D Human-Body Reconstruction

detectron

FAIR's research platform for object detection research, implementing popular algorithms like Mask R-CNN and RetinaNet.

easypyspin

cv2.VideoCapture like wrapper for FLIR Spinnaker SDK

everybody_dance_now_pytorch

A PyTorch Implementation of "Everybody Dance Now" from Berkeley AI lab.

flyai_pose_classification

FLY AI 동작 분류 실습 코드

google-mediapipe

Google MediaPipe Face + Hands + Body + Object

handtracking

Building a Real-time Hand-Detector using Neural Networks (SSD) on Tensorflow

horse-race-betting-recommendation-algorithm

19-2 딥러닝의 기초 기말 프로젝트

imavatar

Official repository for CVPR 2022 paper: I M Avatar: Implicit Morphable Head Avatars from Videos

kekoxtutorial

전 세계의 멋진 케라스 문서 및 튜토리얼을 한글화하여 케라스x코리아를 널리널리 이롭게합니다.

line-fitting-with-ols-tls-and-ransac

Implemented Ordinary Least Squares, Total Least Squares and RANSAC

mediapipe-to-mixamo

mediapipe landmark to mixamo skeleton

mediapipe4u-demo

MediaPipe4U Plugin Demo Project

mediapipe4u-plugin

mmpose

OpenMMLab Pose Estimation Toolbox and Benchmark.

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

objectrecognition_robot

opencap-api

opencap-core

Main OpenCap processing pipeline

opencap-processing

Utilities for processing OpenCap data.

opencap-viewer