zoom1539 Goto Github PK

3d-boundingbox

PyTorch implementation for 3D Bounding Box Estimation Using Deep Learning and Geometry

action-recognition

Three steps to train your own model for action recognition based on CNN and LSTM by PyTorch.

awesome-action-recognition

A curated list of action recognition and related area resources

camera_calibration

Accurate geometric camera calibration with generic camera models

centerhmr

CenterHMR: a bottom-up single-shot method for multi-person 3D mesh recovery from a single image

cmvs-pmvs

This software (CMVS) takes the output of a structure-from-motion (SfM) software as input

crowd_counting_from_scratch

This is an overview and tutorial about crowd counting. In this repository, you can learn how to estimate number of pedestrians in crowd scenes through computer vision and deep learning.

crowdcount-mcnn

Single Image Crowd Counting via MCNN (Unofficial Implementation)

darknet

YOLOv4 - Neural Networks for Object Detection (Windows and Linux version of Darknet )

deep_sort_pytorch

MOT tracking using deepsort and yolov3 with pytorch

dev-docs

服务于极市平台开发者的项目，提供SDK接口文件规范与常见问题示例代码。欢迎所有开发者一起参与示例代码编写。

esp32-camera

fast-reid

SOTA Re-identification Methods and Toolbox

halcon_project

impersonator

PyTorch implementation of our ICCV 2019 paper: Liquid Warping GAN: A Unified Framework for Human Motion Imitation, Appearance Transfer and Novel View Synthesis

learnable-triangulation-pytorch

This repository is an official PyTorch implementation of the paper "Learnable Triangulation of Human Pose" (ICCV 2019, oral). Proposed method archives state-of-the-art results in multi-view 3D human pose estimation!

lffd-with-ncnn

A C++ API of the LFFD with ncnn

line2d

Repo for real-time texture-less object instance detection and tracking.

mesh-to-smpl-renderer

mmskeleton

Spatial Temporal Graph Convolutional Networks (ST-GCN) for Skeleton-Based Action Recognition in PyTorch

monodepth2

[ICCV 2019] Monocular depth estimation from a single image

ms-g3d

PyTorch implementation of "Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition", CVPR 2020 Oral

openmvg

open Multiple View Geometry library. Basis for 3D computer vision and Structure from Motion.

openpose

OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation

pa_detect_tracker

application algorithm: track by detect

pa_human3d

for show

pa_mocap

pa_multi_tracker

application: tracking for multiple classes

pa_tracker

platform applicaton: tracker by detector and reid

pb_detect

basic algorithm: detect