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.

Related

  • Project
    tomas-gajarsky/facetorch

    Facetorch is a Python library for face detection and analysis. It packages open-source deep-learning models into portable, exportable formats and provides a configurable toolkit with components like detectors and predictors.

  • Project
    deepinsight/insightface

    InsightFace is an open‑source 2D/3D face analysis library offering detection, recognition, alignment, video redaction, person‑level matching, and a self‑hosted server with REST API. Implemented in PyTorch/MXNet, it provides pretrained models, automatic hardware backend selection, and tools for large‑scale face search.

  • Project
    facebookresearch/MHR

    A high-fidelity parametric 3D human body model that uses identity, pose, and facial expression parameters to generate realistic, differentiable human meshes.

  • Project
    jacobgil/pytorch-grad-cam

    A PyTorch library for explainable AI in computer vision that provides a wide range of pixel attribution methods to visualize and diagnose model predictions.

  • Project
    cyrusbehr/YOLOv8-TensorRT-CPP

    A C++ implementation of YOLOv8 using TensorRT for high-performance GPU inference, supporting object detection, semantic segmentation, and pose estimation.