Learning to Enhance Low-Light Image via Zero-Reference Deep Curve Estimation
Learning to Enhance Low-Light Image via Zero-Reference Deep Curve Estimation
复制标题
DOI：
10.1109/tpami.2021.3063604
复制
发表时间：
2022-03-03
影响因子：
23.6
通讯作者：
Loy, Chen Change
中科院分区：
文献类型：
--
作者：
Li, Chongyi;Guo, Chunle;Loy, Chen Change
本文提出了一种新的方法，零参考深度曲线估计（Zero-DCE），它将光线增强作为一个具有深度网络的图像特定曲线估计任务。我们的方法训练了一个轻量级的深度网络DCE-Net，以估计给定图像的动态范围调整的像素级和高阶曲线。曲线估计是专门设计的，考虑到像素值范围，单调性和可微性。Zero-DCE在其对参考图像的宽松假设中是有吸引力的，即，它在训练期间不需要任何配对或甚至不需要任何未配对的数据。这是通过一组精心制定的非参考损失函数来实现的，这些函数隐式地测量增强质量并驱动网络的学习。尽管它的简单性，我们表明，它概括以及不同的照明条件。我们的方法是有效的，图像增强可以通过一个直观和简单的非线性曲线映射。我们进一步提出了一个加速和轻型版本的Zero-DCE，称为Zero-DCE++，它利用了一个只有10 K参数的微型网络。Zero-DCE++在保持Zero-DCE的增强性能的同时，具有快速的推理速度（对于大小为1200 x900 x3的图像，在单个GPU/CPU上为1000/11 FPS）。在各种基准上进行的大量实验表明，我们的方法在定性和定量方面优于最先进的方法。此外，我们的方法在黑暗中的人脸检测的潜在好处进行了讨论。源代码可在https://li-chongyi.github.io/Proj_Zero-DCE++.html上公开获取。
This paper presents a novel method, Zero-Reference Deep Curve Estimation (Zero-DCE), which formulates light enhancement as a task of image-specific curve estimation with a deep network. Our method trains a lightweight deep network, DCE-Net, to estimate pixel-wise and high-order curves for dynamic range adjustment of a given image. The curve estimation is specially designed, considering pixel value range, monotonicity, and differentiability. Zero-DCE is appealing in its relaxed assumption on reference images, i.e., it does not require any paired or even unpaired data during training. This is achieved through a set of carefully formulated non-reference loss functions, which implicitly measure the enhancement quality and drive the learning of the network. Despite its simplicity, we show that it generalizes well to diverse lighting conditions. Our method is efficient as image enhancement can be achieved by an intuitive and simple nonlinear curve mapping. We further present an accelerated and light version of Zero-DCE, called Zero-DCE++, that takes advantage of a tiny network with just 10K parameters. Zero-DCE++ has a fast inference speed (1000/11 FPS on a single GPU/CPU for an image of size 1200x900x3) while keeping the enhancement performance of Zero-DCE. Extensive experiments on various benchmarks demonstrate the advantages of our method over state-of-the-art methods qualitatively and quantitatively. Furthermore, the potential benefits of our method to face detection in the dark are discussed. The source code is made publicly available at https://li-chongyi.github.io/Proj_Zero-DCE++.html.