shadow111 Goto Github PK

360deg_from_fisheyecamera

audaces-perps

caffe_ocr

主流ocr算法研究实验性的项目，目前实现了CNN+BLSTM+CTC架构

captain.ui

:red_circle: Captain desktop and in-game recording HUD interface

caricatureface

The source code for paper "Landmark Detection and 3D Face Reconstruction for Caricature using a Nonlinear Parametric Model".

computer-vision

dancing2music

datascience

ecosystem

Project files for Solana ecosystem members

everybodydancenow

Motion Retargeting Video Subjects

explorer

Explorer for Solana clusters

face-vid2vid

fast-neural-style

Feedforward style transfer

fisheye-stereo-calibration

:camera: :camera: Fisheye stereo calibration using OpenCV and C++

folly

An open-source C++ library developed and used at Facebook.

gnucash-ixbrl

iXBRL financial reports creation using data from GnuCash accounts

hethers.js

Complete EVM library in JavaScript/TypeScript for Hedera Hashgraph Smart Contract Service

ixbrl-parse

iXBRL parsing library in Python. Also outputs to RDF and CSV.

mediapipe-holistic-tracking-aar-example

mocapnet

We present MocapNET2, 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 (70 fps in CPU-only execution).

near-wallet

near wallet (extension)

node-x11

nodejs binding that allow screen capture, mouse and keyboard intercation

oasis-sdk

SDK for the Oasis network

object-detection-using-tensorflow-js

Example built for the training of object detection model using TensorFlow.js on pascal voc object detection dataset

object-tracking-js

Track an object as it moves in a video with no training

opencv4nodejs-4.5.2

Opencv Build for Nodejs

raredrops-nft-marketplace

A Decentralized NFT Marketplace on Polygon Testnet that allows users to buy, sell and create NFTs built using Next.js

rps_tfjs_demo

Training a Rock Paper Scissors model in the browser via TFJS - Learn along style

screen-recording

screencapture

A DirectX hardware video + audio capture with mixing capabilities and Media Foundation file encoding (Windows 8+)