MobileMEF: Fast and Efficient Method for Multi-Exposure Fusion

TL;DR

MobileMEF introduces a fast, efficient deep learning-based multi-exposure fusion method optimized for mobile devices, enabling real-time high-quality image processing at 4K resolution with minimal computational resources.

Contribution

The paper presents a novel encoder-decoder architecture with efficient blocks tailored for mobile devices, achieving real-time multi-exposure fusion at high resolutions.

Findings

Processes 4K images in under 2 seconds on mid-range smartphones.

Outperforms state-of-the-art methods in quality and efficiency.

Reduces computational and memory requirements for mobile multi-exposure fusion.

Abstract

Recent advances in camera design and imaging technology have enabled the capture of high-quality images using smartphones. However, due to the limited dynamic range of digital cameras, the quality of photographs captured in environments with highly imbalanced lighting often results in poor-quality images. To address this issue, most devices capture multi-exposure frames and then use some multi-exposure fusion method to merge those frames into a final fused image. Nevertheless, most traditional and current deep learning approaches are unsuitable for real-time applications on mobile devices due to their heavy computational and memory requirements. We propose a new method for multi-exposure fusion based on an encoder-decoder deep learning architecture with efficient building blocks tailored for mobile devices. This efficient design makes our model capable of processing 4K resolution images in less than 2 seconds on mid-range smartphones. Our method outperforms state-of-the-art techniques regarding full-reference quality measures and computational efficiency (runtime and memory usage), making it ideal for real-time applications on hardware-constrained devices. Our code is available at: https://github.com/LucasKirsten/MobileMEF.