MobileMEF: Fast and Efficient Method for Multi-Exposure Fusion
This addresses the need for real-time image fusion on hardware-constrained mobile devices, offering an incremental improvement over existing methods.
They tackled the problem of multi-exposure fusion for high-quality images on mobile devices, proposing a fast and efficient deep learning method that processes 4K images in under 2 seconds on mid-range smartphones and outperforms state-of-the-art techniques in quality and efficiency.
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.