hysts/anime-face-detector
Anime Face Detector using mmdet and mmpose
What it solves
It provides a way to automatically detect anime-style faces in images and estimate their facial landmarks, which is often difficult for standard human face detectors.
How it works
The project uses PyTorch to run pretrained models for both detection and landmark estimation. It offers a choice between Faster R-CNN and YOLOv3 for detecting the bounding boxes of near-frontal anime faces, and uses an HRNetV2 model to predict 28 specific landmark points on the face.
Who it’s for
Developers and researchers working with anime-style imagery who need to locate faces and identify key facial features for further processing.
Highlights
- Multiple Detection Options: Supports both Faster R-CNN and YOLOv3 architectures.
- Landmark Estimation: Predicts 28 distinct facial landmark points.
- Simplified Dependencies: Runs in plain PyTorch without requiring the OpenMMLab runtime.
- Easy Integration: Provides a simple Python API and automatic weight downloading via Hugging Face Hub.