# HRNet/HigherHRNet-Human-Pose-Estimation

This is an official implementation of our CVPR 2020 paper "HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation" (https://arxiv.org/abs/1908.10357)

Repository: https://github.com/HRNet/HigherHRNet-Human-Pose-Estimation
Canonical: https://ross.abutalabs.com/products/higherhrnet-human-pose-estimation
Language: Python
License: MIT
License Family: permissive
Last push: 2021-04-12T00:51:39+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2562, "days_push": 1970, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1463, forks 284 (observed 2026-08-28T04:04:47.760628+00:00)

## What it is
Official PyTorch implementation of HigherHRNet, a CVPR 2020 bottom-up multi-person human pose estimation model using scale-aware high-resolution feature pyramids. It includes training and evaluation code plus pretrained models for COCO and CrowdPose datasets.

## Use cases
- detect and estimate poses of multiple people in an image
- improve keypoint localization for small persons in crowded scenes
- train a bottom-up pose estimation model on COCO or CrowdPose
- benchmark pose estimation models against state-of-the-art AP scores
- use pretrained HigherHRNet weights for downstream research

## When to choose
- you need bottom-up multi-person pose estimation robust to scale variation
- your scenes are crowded or contain small persons
- you want a research-grade reference implementation with pretrained models

## When to avoid
- you need top-down single-person pose estimation
- you want a production-ready maintained library with frequent updates
- you lack GPU resources for training or inference

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, computer-vision, image-processing
- domain: computer-vision, deep-learning, machine-learning
- platform: python
- tags: human-pose-estimation, bottom-up-pose-estimation, hrnet, cvpr-2020, pytorch, keypoint-detection, research-code, linux, gpu

## Member repositories
- HRNet/HigherHRNet-Human-Pose-Estimation (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:47.760628+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:35:11.289456+00:00, confidence not recorded.
  - readme: https://github.com/HRNet/HigherHRNet-Human-Pose-Estimation (fetched 2026-08-28T04:04:47.760628+00:00, sha 14e05e58b70f)
- Data as of 2026-08-30T08:39:29.467469+00:00.