arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2501.09718cs.CVcs.RO
收藏

FLOL:面向真实世界的快速低光照增强基线

FLOL: Fast Baselines for Real-World Low-Light Enhancement

Cidaut AI

Juan C. Benito, Daniel Feijoo, Alvaro Garcia, Marcos V. Conde

AI总结:

FLOL提出了一种轻量级神经网络,结合频率域和空间域图像处理,实现快速且高效的低光照图像增强,适用于真实世界场景。

摘要:

低光照图像增强(LLIE)是计算摄影和成像中的关键任务。增强在夜间或黑暗环境中捕获的图像的问题已在计算机视觉文献中得到了充分研究。然而,当前基于深度学习的解决方案在真实世界场景中(例如噪声环境或饱和像素的场景)在效率和鲁棒性方面存在困难。我们提出了一种轻量级的神经网络,结合频率域和空间域的图像处理。我们的基线方法FLOL是该任务中最快的模型之一,在流行的现实世界基准如LOLv2、LSRW、MIT-5K和UHD-LL上实现了与最新技术相当的结果。此外,我们能够在12毫秒内实时处理1080p图像。代码和模型见https://github.com/cidautai/FLOL

英文摘要:

Low-Light Image Enhancement (LLIE) is a key task in computational photography and imaging. The problem of enhancing images captured during night or in dark environments has been well-studied in the computer vision literature. However, current deep learning-based solutions struggle with efficiency and robustness for real-world scenarios (e.g., scenes with noise, saturated pixels). We propose a lightweight neural network that combines image processing in the frequency and spatial domains. Our baseline method, FLOL, is one of the fastest models for this task, achieving results comparable to the state-of-the-art on popular real-world benchmarks such as LOLv2, LSRW, MIT-5K and UHD-LL. Moreover, we are able to process 1080p images in real-time under 12ms. Code and models at https://github.com/cidautai/FLOL

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑