HRNet/HigherHRNet-Human-Pose-Estimation

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1463 stars · 284 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

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

library · maturity maintenance

machine-learning deep-learning computer-vision image-processing computer-vision deep-learning machine-learning python human-pose-estimation bottom-up-pose-estimation hrnet cvpr-2020 pytorch keypoint-detection research-code linux gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="HRNet/HigherHRNet-Human-Pose-Estimation")