FoxNet: A Multi-face Alignment Method

TL;DR

FoxNet introduces a fast, bottom-up multi-face alignment method that accurately localizes facial landmarks for multiple faces simultaneously, outperforming existing approaches in speed and precision.

Contribution

This work presents a novel bottom-up architecture for multi-face alignment that achieves high speed and accuracy, along with a new dataset for benchmarking.

Findings

High precision in multi-face landmark localization

Significantly faster than top-down methods

Effective on a new publicly available dataset

Abstract

Multi-face alignment aims to identify geometry structures of multiple faces in an image, and its performance is essential for the many practical tasks, such as face recognition, face tracking, and face animation. In this work, we present a fast bottom-up multi-face alignment approach, which can simultaneously localize multi-person facial landmarks with high precision.In more detail, our bottom-up architecture maps the landmarks to the high-dimensional space with which landmarks of all faces are represented. By clustering the features belonging to the same face, our approach can align the multi-person facial landmarks synchronously.Extensive experiments show that our method can achieve high performance in the multi-face landmark alignment task while our model is extremely fast. Moreover, we propose a new multi-face dataset to compare the speed and precision of bottom-up face alignment method with top-down methods. Our dataset is publicly available at https://github.com/AISAResearch/FoxNet