1adrianb/face-alignment Alternatives

comprehensive face analysis framework with landmark models; pick when you also need recognition/attributes.

State-of-the-art 2D and 3D Face Analysis Project

pose-guided 6DoF face alignment approach; choose if you need camera pose alongside landmarks.

The official PyTorch implementation of img2pose: Face Alignment and Detection via 6DoF, Face Pose Estimation - CVPR 2021

dense 3D face alignment with full-pose support; pick when you need 3D mesh rather than sparse landmarks.

The official PyTorch implementation of Towards Fast, Accurate and Stable 3D Dense Face Alignment, ECCV 2020.

unified face analysis library with landmark/face-mesh; pick when you want a single API for many face tasks.

UniFace: A Unified Face Analysis Library for Python | Detection, alignment, landmarks, face-mesh, recognition, parsing, gaze, attributes and anti-spoofing under one API.

full SDK with landmarks, liveness, and recognition; pick when you need those additional features.

Face Recognition, Face Liveness Detection, Face Anti-Spoofing, Face Detection, Face Landmarks, Face Compare, Face Matching, Face Pose, Face Expression, Face Attributes, Face Templates Extraction, Face Landmarks

maintained PyTorch face analysis library; pick when you need alignment plus detection/recognition.

Python library for analysing faces using PyTorch

older 3DMM-based dense 3D alignment, superseded by V2; choose for a PyTorch 3D baseline if you accept age.

The PyTorch improved version of TPAMI 2017 paper: Face Alignment in Full Pose Range: A 3D Total Solution.

legacy Caffe face analysis suite with alignment; only for historical baseline use.

Face analysis mainly based on Caffe. At this time, face analysis tasks like detection, alignment and recognition have been done.

MATLAB MTCNN for joint detection and 5-point alignment; pick for a classic CPU baseline in MATLAB.

Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Neural Networks

PyTorch MTCNN for 5-point detection/alignment; lightweight but outdated and lacks 3D.

Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks

C++ boundary-aware landmark research code; use to reproduce CVPR 2018 results.

[CVPR 2018] Look at Boundary: A Boundary-Aware Face Alignment Algorithm

old PyTorch landmark detector for 68/39 2D points; viable for simple 2D only and accepts no maintenance.

Fast and accurate face landmark detection library using PyTorch; Support 68-point semi-frontal and 39-point profile landmark detection; Support both coordinate-based and heatmap-based inference; Up to 100 FPS landmark inference speed with SOTA face detector on CPU.

mobile C++ SDK for face detection/landmarks; choose for on-device inference without PyTorch.

TengineKit - Free, Fast, Easy, Real-Time Face Detection & Face Landmarks & Face Attributes & Hand Detection & Hand Landmarks & Body Detection & Body Landmarks & Iris Landmarks & Yolov5 SDK On Mobile.

HRNet-based landmark detection research code; good 2D accuracy but unmaintained and no 3D.

This is an official implementation of facial landmark detection for our TPAMI paper "Deep High-Resolution Representation Learning for Visual Recognition". https://arxiv.org/abs/1908.07919

mobile C++ real-time landmark detector; choose for embedded/low-latency use.

Deep Learning Based Free Mobile Real-Time Face Landmark Detector. Contact:[email protected]