DeeplabcutOfficial implementation of DeepLabCut: Markerless pose estimation of user-defined features with deep learning for all animals incl. humans
Stars: ✭ 2,550 (+4803.85%)
sleapA deep learning framework for multi-animal pose tracking.
Stars: ✭ 200 (+284.62%)
MultipersonCode repository for the paper: "Coherent Reconstruction of Multiple Humans from a Single Image" in CVPR'20
Stars: ✭ 212 (+307.69%)
icra20-hand-object-pose[ICRA 2020] Robust, Occlusion-aware Pose Estimation for Objects Grasped by Adaptive Hands
Stars: ✭ 42 (-19.23%)
HopeSource code of CVPR 2020 paper, "HOPE-Net: A Graph-based Model for Hand-Object Pose Estimation"
Stars: ✭ 184 (+253.85%)
AmassData preparation and loader for AMASS
Stars: ✭ 180 (+246.15%)
DeepmatchvoImplementation of ICRA 2019 paper: Beyond Photometric Loss for Self-Supervised Ego-Motion Estimation
Stars: ✭ 178 (+242.31%)
Swiftopenposetf-openpose Based iOS Project
Stars: ✭ 215 (+313.46%)
movenet.pytorchA Pytorch implementation of MoveNet from Google. Include training code and pre-trained model.
Stars: ✭ 273 (+425%)
Improved Body PartsSimple Pose: Rethinking and Improving a Bottom-up Approach for Multi-Person Pose Estimation
Stars: ✭ 202 (+288.46%)
CenterNet-pytorch-lightningRefactored implementation of CenterNet (Objects as Points - Zhou, Xingyi et. al.) shipping with PyTorch Lightning modules
Stars: ✭ 53 (+1.92%)
Multiposenet.pytorchpytorch implementation of MultiPoseNet (ECCV 2018, Muhammed Kocabas et al.)
Stars: ✭ 191 (+267.31%)
A2jCode for paper "A2J: Anchor-to-Joint Regression Network for 3D Articulated Pose Estimation from a Single Depth Image". ICCV2019
Stars: ✭ 190 (+265.38%)
Pose2poseThis is a pix2pix demo that learns from pose and translates this into a human. A webcam-enabled application is also provided that translates your pose to the trained pose. Everybody dance now !
Stars: ✭ 182 (+250%)
FASSEG-repositoryDatasets for multi-class and multi-pose face segmentation
Stars: ✭ 66 (+26.92%)
OchumanapiAPI for the dataset proposed in "Pose2Seg: Detection Free Human Instance Segmentation" @ CVPR2019.
Stars: ✭ 168 (+223.08%)
MotionPlannerMotion Planner for Self Driving Cars
Stars: ✭ 129 (+148.08%)
realantRealAnt robot platform for low-cost, real-world reinforcement learning
Stars: ✭ 40 (-23.08%)
Lili OmLiLi-OM is a tightly-coupled, keyframe-based LiDAR-inertial odometry and mapping system for both solid-state-LiDAR and conventional LiDARs.
Stars: ✭ 159 (+205.77%)
SynthdetSynthDet - An end-to-end object detection pipeline using synthetic data
Stars: ✭ 148 (+184.62%)
Posenet CoremlI checked the performance by running PoseNet on CoreML
Stars: ✭ 143 (+175%)
OwlyshieldOwlyshield is an EDR framework designed to safeguard vulnerable applications from potential exploitation (C&C, exfiltration and impact))..
Stars: ✭ 281 (+440.38%)
aistplusplus apiAPI to support AIST++ Dataset: https://google.github.io/aistplusplus_dataset
Stars: ✭ 277 (+432.69%)
Deepposekita toolkit for pose estimation using deep learning
Stars: ✭ 233 (+348.08%)
MocapnetWe 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).
Stars: ✭ 194 (+273.08%)
Crowd Behavior AnalysisCrowd behavior analysis is an important field of research in modern world. It has wide applications in surveillance and public safety which are one of the prime social concerns. One way to analyze crowd behavior is obtain crowd movement data and then find out outliers in the individual trajectories to infer any abnormal behavior in the crowd.
Stars: ✭ 31 (-40.38%)
MobilePose-PiMobilePose deployment for Raspberry Pi
Stars: ✭ 15 (-71.15%)
ssjSocial Signal Processing for Android
Stars: ✭ 24 (-53.85%)
3DObjectTrackingOfficial Code: A Sparse Gaussian Approach to Region-Based 6DoF Object Tracking
Stars: ✭ 375 (+621.15%)
Densereg3D hand pose estimation via dense regression
Stars: ✭ 176 (+238.46%)
telemetryOpen-source datasets for anyone interested in working with network anomaly based machine learning, data science and research
Stars: ✭ 93 (+78.85%)
HandposeA python program to detect and classify hand pose using deep learning techniques
Stars: ✭ 168 (+223.08%)
PeekingDuckA modular framework built to simplify Computer Vision inference workloads.
Stars: ✭ 143 (+175%)
Augmented reality💎 "Marker-less Augmented Reality" with OpenCV and OpenGL.
Stars: ✭ 165 (+217.31%)
NSRMhand[WACV 2020] "Nonparametric Structure Regularization Machine for 2D Hand Pose Estimation"
Stars: ✭ 95 (+82.69%)
People Counting PoseOdin: Pose estimation-based tracking and counting of people in videos
Stars: ✭ 147 (+182.69%)
Monoloco[ICCV 2019] Official implementation of "MonoLoco: Monocular 3D Pedestrian Localization and Uncertainty Estimation" in PyTorch + Social Distancing
Stars: ✭ 242 (+365.38%)
Gccpm Look Into Person Cvpr19.pytorchFast and accurate single-person pose estimation, ranked 10th at CVPR'19 LIP challenge. Contains implementation of "Global Context for Convolutional Pose Machines" paper.
Stars: ✭ 137 (+163.46%)
tf-cpnCascade Pyramid Netwrok
Stars: ✭ 22 (-57.69%)
Map Based Visual LocalizationA general framework for map-based visual localization. It contains 1) Map Generation which support traditional features or deeplearning features. 2) Hierarchical-Localizationvisual in visual(points or line) map. 3)Fusion framework with IMU, wheel odom and GPS sensors.
Stars: ✭ 229 (+340.38%)
SF-GRUPedestrian Action Anticipation using Contextual Feature Fusion in Stacked RNNs
Stars: ✭ 43 (-17.31%)
qml-arSeamless Augmented Reality module for QML using UchiyaMarkers
Stars: ✭ 32 (-38.46%)
trt pose handReal-time hand pose estimation and gesture classification using TensorRT
Stars: ✭ 137 (+163.46%)