Abstract
Although significant progress has been made in enhancing visibility, retrieving texture details, and mitigating noise in Low-Light (LL) images, the challenge persists in applying current Low-Light Image Enhancement (LLIE) methods to real-world scenarios, primarily due to the diverse illumination conditions encountered. Furthermore, the quest for generating enhancements that are visually realistic and attractive remains an underexplored realm. In response to these challenges, we introduce a novel \textbf{LLIE} framework with the guidance of \textbf{G}enerative \textbf{P}erceptual \textbf{P}riors (\textbf{GPP-LLIE}) derived from vision-language models (VLMs). Specifically, we first propose a pipeline that guides VLMs to assess multiple visual attributes of the LL image and quantify the assessment to output the global and local perceptual priors. Subsequently, to incorporate these generative perceptual priors to benefit LLIE, we introduce a transformer-based backbone in the diffusion process, and develop a new layer normalization (\textit{\textbf{GPP-LN}}) and an attention mechanism (\textit{\textbf{LPP-Attn}}) guided by global and local perceptual priors. Extensive experiments demonstrate that our model outperforms current SOTA methods on paired LL datasets and exhibits superior generalization on real-world data. The code is released at \url{this https URL}.
Abstract (translated)
尽管在增强低光（LL）图像的可见性、纹理细节恢复和降噪方面已经取得了显著进展，但当前的低光图像增强（LLIE）方法难以应用于现实世界的场景中，主要是因为遇到的照明条件千变万化。此外，生成既视觉上真实又吸引人的图像改进仍是未充分探索的研究领域。为应对这些挑战，我们提出了一种新的低光图像增强框架，并引入了由视觉-语言模型（VLMs）指导的生成感知先验（GPP-LLIE）。具体而言，首先我们提出了一个管道，引导VLM评估低光图像的多个视觉属性，并将评估量化为全局和局部感知先验输出。随后，为了在扩散过程中利用这些生成感知先验来提升LLIE的效果，我们引入了一个基于变压器的基础架构，并开发了一种新的归一化层（GPP-LN）以及一种由全局和局部感知先验指导的注意力机制（LPP-Attn）。广泛的实验表明，我们的模型在配对低光数据集上超越了当前最先进的方法，并且在现实世界的数据中表现出更强的泛化能力。代码可在[此处](此链接指向原始文本中的URL)获取。
URL
https://arxiv.org/abs/2412.20916
