Xingyi Zhou

CenterNet. Object detection, 3D detection, and pose estimation using center point detection:

CenterTrack. Simultaneous object detection and tracking using center points.

CenterNet2. Two-stage CenterNet

ExtremeNet. Bottom-up Object Detection by Grouping Extreme and Center Points

pytorch-pose-hg-3d. PyTorch implementation for 3D human pose estimation

UniDet. Object detection on multiple datasets with an automatically learned unified label space.

GTR. Global Tracking Transformers, CVPR 2022

pose-hg-3d. Code repository for Towards 3D Human Pose Estimation in the Wild: a Weakly-supervised Approach

DeepModel. Code repository for Model-based Deep Hand Pose Estimation

StarMap. StarMap for Category-Agnostic Keypoint and Viewpoint Estimation

3DKeypoints-DA. Unsupervised Domain Adaptation for 3D Keypoint Estimation via View Consistency

Randomforest_Hand_Detector. My implementation of random forest hand detector from depth image

random-forest-classifier. my implementation of standard random forest classifier

CenterNet-better. An easy to understand and better performance version of CenterNet

3D-Machine-Learning. A learning resource repository for 3D machine learning

Bubble-game. my implementation of a simple bubble game

Det3D. A general 3D object detection codebse.

mmdetection. Open MMLab Detection Toolbox

TensorRT-CenterNet. tensorrt5 , centernet , centerface, deform conv, int8

deepcut. Multi Person Pose Estimation

awesome-public-datasets. An awesome list of high-quality open datasets in public domains (on-going). By everyone, for everyone.

models. Models and examples built with TensorFlow

cocoapi. COCO API - Dataset @ http://cocodataset.org/

FLY_US. 美国大学备考资料

human-pose-estimation.pytorch. The project is official implement of our ECCV2018 paper "Simple Baselines for Human Pose Estimation and Tracking(https://arxiv.org/abs/1804.06208)"

Deep3DPose. Jupyter Notebook

object3d. Code for "6-DoF Object Pose from Semantic Keypoints", ICRA 2017

Higher-HRNet-Human-Pose-Estimation. Higher-Resolution Networks (HigherHRNets) for Human Pose Estimation

pytorch-faster-rcnn. I would appreciate if someone can retrain the model. The "finetune from scratch" result should be better because the training details have been changed. (And mobilenet training not supported yet.)

DensePose. A real-time approach for mapping all human pixels of 2D RGB images to a 3D surface-based model of the body

CornerNet-Lite. Python

towards-universal-object-detection. Python

tracking_wo_bnw. Implementation of "Tracking without bells and whistles” and the multi-object tracking "Tracktor"

3dmatch-toolbox. 3DMatch - a 3D ConvNet-based local geometric descriptor for aligning 3D meshes and point clouds.

maskrcnn-benchmark. Fast, modular reference implementation of Instance Segmentation and Object Detection algorithms in PyTorch.

nuscenes-devkit. The devkit of the nuScenes dataset.

deep-high-resolution-net.pytorch. The project is an official implement of our CVPR2019 paper "Deep High-Resolution Representation Learning for Human Pose Estimation"

mseg-semantic. An Official Repo of CVPR '20 "MSeg: A Composite Dataset for Multi-Domain Segmentation"

flax. Flax is a neural network library for JAX that is designed for flexibility.

pytorch_HMR. pytorch version of "End-to-end Recovery of Human Shape and Pose"

NTS-Net. This is a PyTorch implementation of the ECCV2018 paper "Learning to Navigate for Fine-grained Classification" (Ze Yang, Tiange Luo, Dong Wang, Zhiqiang Hu, Jun Gao, Liwei Wang).

dataset. The Open Images dataset

integral-human-pose. Integral Human Pose Regression

holistic_scene_parsing. Code for ECCV 2018 paper - Holistic 3D Scene Parsing and Reconstruction from a Single RGB Image

3DHumanPose. MATLAB

ASFF. yolov3 with mobilenet v2 and ASFF

3DMPPE_POSENET_RELEASE. Official PyTorch implementation of "Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Image ", ICCV 2019

lcnn. End-to-End Wireframe Parsing

CornerNet. Python

resume. An elegant \LaTeX\ résumé template