arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1808.04560cs.CV
收藏

用于弱光增强的深度Retinex分解

Deep Retinex Decomposition for Low-Light Enhancement

Peking University(北京大学)

Chen Wei, Wenjing Wang, Wenhan Yang, Jiaying Liu

摘要:

Retinex模型是微光图像增强的有效工具。它假设观测图像可以分解为反射率和照明。大多数现有的基于Retinex的方法都为这种高度不适定的分解精心设计了手工制作的约束和参数,当应用于各种场景时,这些约束和参数可能会受到模型容量的限制。在本文中,我们收集了一个包含低/正常光图像对的低光数据集(LOL),并提出了一个在该数据集上学习的深度Retinex-Net,包括用于分解的Decom-Net和用于照明调整的Enhance-Net。在Decom-Net的训练过程中,没有分解的反射率和光照的基础事实。该网络仅使用关键约束进行学习,包括成对的低/正常光图像共享的一致反射率以及照明的平滑度。在分解的基础上,通过增强网络Enhance-Net对光照进行亮度增强,并对反射率进行联合去噪。Retinex-Net是端到端可训练的,因此学习的分解本质上有利于亮度调整。大量的实验表明,我们的方法不仅实现了视觉上令人愉快的质量低光增强,但也提供了一个很好的代表性的图像分解。

英文摘要:

Retinex model is an effective tool for low-light image enhancement. It assumes that observed images can be decomposed into the reflectance and illumination. Most existing Retinex-based methods have carefully designed hand-crafted constraints and parameters for this highly ill-posed decomposition, which may be limited by model capacity when applied in various scenes. In this paper, we collect a LOw-Light dataset (LOL) containing low/normal-light image pairs and propose a deep Retinex-Net learned on this dataset, including a Decom-Net for decomposition and an Enhance-Net for illumination adjustment. In the training process for Decom-Net, there is no ground truth of decomposed reflectance and illumination. The network is learned with only key constraints including the consistent reflectance shared by paired low/normal-light images, and the smoothness of illumination. Based on the decomposition, subsequent lightness enhancement is conducted on illumination by an enhancement network called Enhance-Net, and for joint denoising there is a denoising operation on reflectance. The Retinex-Net is end-to-end trainable, so that the learned decomposition is by nature good for lightness adjustment. Extensive experiments demonstrate that our method not only achieves visually pleasing quality for low-light enhancement but also provides a good representation of image decomposition.

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。

↑