Abstract
The following three factors restrict the application of existing low-light image enhancement methods: unpredictable brightness degradation and noise, inherent gap between metric-favorable and visual-friendly versions, and the limited paired training data. To address these limitations, we propose an implicit Neural Representation method for Cooperative low-light image enhancement, dubbed NeRCo. It robustly recovers perceptual-friendly results in an unsupervised manner. Concretely, NeRCo unifies the diverse degradation factors of real-world scenes with a controllable fitting function, leading to better robustness. In addition, for the output results, we introduce semantic-orientated supervision with priors from the pre-trained vision-language model. Instead of merely following reference images, it encourages results to meet subjective expectations, finding more visual-friendly solutions. Further, to ease the reliance on paired data and reduce solution space, we develop a dual-closed-loop constrained enhancement module. It is trained cooperatively with other affiliated modules in a self-supervised manner. Finally, extensive experiments demonstrate the robustness and superior effectiveness of our proposed NeRCo. Our code is available at this https URL.
Abstract (translated)
以下是三个因素限制了现有低光图像增强方法的应用:不可预测的亮度下降和噪声,metrics favorable和视觉友好版本的固有差异,以及有限的配对训练数据。为了解决这些问题,我们提出了一种隐含的神经网络表示方法,称为NeRCo,它以无监督的方式 robustly 恢复认知友好的结果。具体来说,NeRCo将真实场景的不同退化因素与可控制适应函数相结合,导致更好的鲁棒性。此外,对于输出结果,我们引入了语义导向的监督,从预训练的视觉语言模型中获取先验。相反,它不再仅仅跟随参考图像,而是鼓励结果满足主观期望,找到更多的视觉友好解决方案。进一步,为了减轻依赖配对数据并减少解决方案空间,我们开发了双重闭环限制增强模块。它与其他相关模块合作训练自我监督。最后,广泛的实验证明了我们提出的NeRCo的鲁棒性和优越性能。我们的代码可用在这个httpsURL上。
URL
https://arxiv.org/abs/2303.11722
