AE-Netv2: Optimization of Image Fusion Efficiency and Network Architecture

TL;DR

AE-Netv2 is an efficient, brain-inspired image fusion method that optimizes network architecture for high-speed, robust performance across various tasks, surpassing existing deep learning approaches.

Contribution

The paper introduces AE-Netv2, a novel autonomous evolution-based image fusion network inspired by human cognition, focusing on architecture and pooling layer effects for improved efficiency and quality.

Findings

Achieves real-time fusion at 100+ FPS on GTX 2070

Outperforms state-of-the-art methods in speed, size, and robustness

Provides insights into architecture and pooling layer influence on fusion quality

Abstract

Existing image fusion methods pay few research attention to image fusion efficiency and network architecture. However, the efficiency and accuracy of image fusion has an important impact in practical applications. To solve this problem, we propose an \textit{efficient autonomous evolution image fusion method, dubed by AE-Netv2}. Different from other image fusion methods based on deep learning, AE-Netv2 is inspired by human brain cognitive mechanism. Firstly, we discuss the influence of different network architecture on image fusion quality and fusion efficiency, which provides a reference for the design of image fusion architecture. Secondly, we explore the influence of pooling layer on image fusion task and propose an image fusion method with pooling layer. Finally, we explore the commonness and characteristics of different image fusion tasks, which provides a research basis for further research on the continuous learning characteristics of human brain in the field of image fusion. Comprehensive experiments demonstrate the superiority of AE-Netv2 compared with state-of-the-art methods in different fusion tasks at a real time speed of 100+ FPS on GTX 2070. Among all tested methods based on deep learning, AE-Netv2 has the faster speed, the smaller model size and the better robustness.