sarsigmadelta Goto Github PK

generalizedmedseg

Recent progress on domain adaption/generalization for medical image segmentation

gitchat-three.js

Three.js达人课相关案例

gpu_stereo_image_proc

Stereo and image rectification and disparity processing with NVIDIA VisionWorks and fixstars libSGM

gstreamer-example

Gstreamer开发教程。

handposebarracuda

Hand and finger tracking solution (MediaPipe Hands) for Unity Barracuda

hardware-effects-gpu

Demonstration of various hardware effects on CUDA GPUs.

hurlex-doc

hurlex 小内核分章节代码和文档

iciar2018

Our solution for ICIAR 2018 Grand Challenge

ik

Minimal Inverse Kinematics library

image_segmentation

Pytorch implementation of U-Net, R2U-Net, Attention U-Net, and Attention R2U-Net.

integrated-development-environment

Visual Studio Code, Visual Studio, Anaconda

jetbot-ros2

ROS 2 implementation of a Teleoperated robot with live video feed using webrtc and SLAM using realsense's stereocameras. Running on a Jetson Nano

kandinsky-2

Kandinsky 2 — multilingual text2image latent diffusion model

keras-yolo2

Easy training on custom dataset. Various backends (MobileNet and SqueezeNet) supported. A YOLO demo to detect raccoon run entirely in brower is accessible at https://git.io/vF7vI (not on Windows).

learn-webgl

This repo contains the code used in the Learn WebGL series on the Invent Box Youtube channel.

learnopencv

Learn OpenCV : C++ and Python Examples

libsgm

Stereo Semi Global Matching by cuda

lightweight-human-pose-estimation-3d-demo.pytorch

Real-time 3D multi-person pose estimation demo in PyTorch. OpenVINO backend can be used for fast inference on CPU.

lightweight-human-pose-estimation.pytorch

Fast and accurate human pose estimation in PyTorch. Contains implementation of "Real-time 2D Multi-Person Pose Estimation on CPU: Lightweight OpenPose" paper.

lightweight_multi_tracker

In this repo , a lightweight multi-objects tracker was implemented . and tested on tools datasets.

machine-learning-session

madman

metrabs

This is a computer vision algorithm that takes a single RGB image as the input and estimates 3D human poses as the output.

metrabs_trt

Running 3D HPE at 30fps

mmaction

An open-source toolbox for action understanding based on PyTorch

mmaction2

OpenMMLab's Next Generation Action Understanding Toolbox and Benchmark

mobilenetv2-poseestimation

Tensorflow based Fast Pose estimation. OpenVINO, Tensorflow Lite, NCS, NCS2 + Python.

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).

monocular-visual-odometry

A simple monocular visual odometry (part of vSLAM) by ORB keypoints with initialization, tracking, local map and bundle adjustment. (WARNING: Hi, I'm sorry that this project is tuned for course demo, not for real world applications !!!)

motionet

A deep neural network that directly reconstructs the motion of a 3D human skeleton from monocular video [ToG 2020]