轻量级网络融合频域与空间域，实现实时低光图像增强。
FLOL: Fast Baselines for Real-World Low-Light Enhancement
- 结合频域与空间域处理，设计轻量网络提升效率。
- 1080p图像处理速度低于12ms，实时性优异。
- 在LOLv2等数据集上效果媲美顶尖模型，适合部署落地。
低光图像增强（LLIE）是计算摄影与成像中的关键任务。尽管该问题在计算机视觉领域已有广泛研究，但现有深度学习方法在真实场景（如含噪声、过曝像素）下仍存在效率与鲁棒性不足的问题。本文提出一种轻量级神经网络，融合频域与空间域的图像处理机制。所提基线模型FLOL是当前最快的方法之一，在LOLv2、LSRW、MIT-5K和UHD-LL等主流真实世界基准上表现接近最先进水平。此外，可在12ms内完成1080p图像的实时处理。代码与模型已开源于https://github.com/cidautai/FLOL。
原文摘要 · Abstract (English)
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
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。