natanielruiz/deep-head-pose

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

1666 stars · 367 forks observed · 2026-08-28

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

Hopenet is a PyTorch deep learning model for fine-grained head pose estimation from images and video, without requiring facial keypoints. It ships pre-trained models on the 300W-LP dataset and scripts for testing on videos using dlib or custom face detections.

Use cases

• estimate head pose from images or video
• estimate yaw pitch roll of a face with deep learning
• run head pose estimation on video frames with face detection
• use a pretrained head pose network in a research project
• track head orientation for gaze or driver monitoring applications

When to choose

• you need accurate head pose angles (yaw, pitch, roll) from a PyTorch model
• you want pretrained weights and video inference scripts out of the box
• you are doing research on head pose or gaze estimation and want a CVPR-published baseline

When to avoid

• you need a maintained production library with active support or a permissive license
• you have no GPU available, since inference currently requires one
• you need keypoint-based or lightweight CPU-only head pose estimation

Facets

library · maturity maintenance

deep-learning computer-vision image-processing machine-learning computer-vision deep-learning machine-learning artificial-intelligence python head-pose-estimation hopenet gaze-estimation pytorch face-pose pretrained-models cvpr gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="natanielruiz/deep-head-pose")