Real-time Memory Efficient Large-pose Face Alignment via Deep Evolutionary Network

TL;DR

This paper introduces a memory-efficient, real-time face alignment method capable of handling large pose variations by combining 3D diffusion heap maps with a deep evolutionary network, significantly improving speed and accuracy.

Contribution

The authors propose a novel deep evolutionary model with 3D DHM and an efficient network structure, enabling fast, accurate face alignment under extreme poses.

Findings

Model is 6 times faster than state-of-the-art on CPU

Model is 14 times faster than state-of-the-art on GPU

Outperforms existing methods especially in large-pose scenarios

Abstract

There is an urgent need to apply face alignment in a memory-efficient and real-time manner due to the recent explosion of face recognition applications. However, impact factors such as large pose variation and computational inefficiency, still hinder its broad implementation. To this end, we propose a computationally efficient deep evolutionary model integrated with 3D Diffusion Heap Maps (DHM). First, we introduce a sparse 3D DHM to assist the initial modeling process under extreme pose conditions. Afterward, a simple and effective CNN feature is extracted and fed to Recurrent Neural Network (RNN) for evolutionary learning. To accelerate the model, we propose an efficient network structure to accelerate the evolutionary learning process through a factorization strategy. Extensive experiments on three popular alignment databases demonstrate the advantage of the proposed models over the state-of-the-art, especially under large-pose conditions. Notably, the computational speed of our model is 6 times faster than the state-of-the-art on CPU and 14 times on GPU. We also discuss and analyze the limitations of our models and future research work.