Help finding an appropriate model for human pose estimation

• openpose

  36 29,867 5.1 C++

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

  

Openpose: This is supposedly realtime (I assume on a gpu, 24fps?) and they provide training code

• lightweight-human-pose-estimation.pytorch

  2 2,022 0.0 Python

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

Lightweight OpenPose: Runs in realtime >20fps confirmed, training code is provided

• InfluxDB

  www.influxdata.com sponsored

  Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.

  

• mediapipe

  49 25,405 9.9 C++

  Cross-platform, customizable ML solutions for live and streaming media.

  

mediapipe: runs in realtime > 20fps confirmed, training code is NOT provided

• tfjs-models

  50 13,698 7.7 TypeScript

  Pretrained models for TensorFlow.js

  

posenet: No training code, can one even train tfjs models?

• tfjs

  29 18,110 8.6 TypeScript

  A WebGL accelerated JavaScript library for training and deploying ML models.

  

posenet: No training code, can one even train tfjs models?

• BlazePose-tensorflow

  1 109 2.6 Python

  A third-party Tensorflow Implementation for paper "BlazePose: On-device Real-time Body Pose tracking".

blazepose: havent tried it yet, looks like tf implementation, but no discussion bout speed. Training code included

• AlphaPose

  4 7,716 0.0 Python

  Real-Time and Accurate Full-Body Multi-Person Pose Estimation&Tracking System

  

alphapose: havent tried it, but looks to run at 16fps (maybe faster?) but is only intended for research not commercial. Training script available.

• WorkOS

  workos.com sponsored

  The modern identity platform for B2B SaaS. The APIs are flexible and easy-to-use, supporting authentication, user identity, and complex enterprise features like SSO and SCIM provisioning.

  

• UniPose

  1 203 0.0 Python

  We propose UniPose, a unified framework for human pose estimation, based on our “Waterfall” Atrous Spatial Pooling architecture, that achieves state-of-art-results on several pose estimation metrics. Current pose estimation methods utilizing standard CNN architectures heavily rely on statistical postprocessing or predefined anchor poses for joint localization. UniPose incorporates contextual seg- mentation and joint localization to estimate the human pose in a single sta

• deep-high-resolution-net.pytorch

  4 4,190 0.0 Cuda

  The project is an official implementation of our CVPR2019 paper "Deep High-Resolution Representation Learning for Human Pose Estimation"

Suggest a related project