Learning to Enhance Low-Light Image via Zero-Reference Deep Curve Estimation
S-Lab, Nanyang Technological University（新加坡南洋理工大学S-Lab）；College of Computer Science, Nankai University（南开大学计算机学院）
Chongyi Li, Chunle Guo, Chen Change Loy
备注：
This work is an extension of our earlier conference version arXiv:2001.06826 (Zero-DCE) that has appeared in CVRP2020. This paper was accepted by TPAMI
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 1200*900*3) 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 will be made publicly available at https://li-chongyi.github.io/Proj_Zero-DCE++.html.
Universidade Federal do Espírito Santo（圣埃斯皮里图联邦大学）
This paper uses robust statistics and curvelet transform to learn a general-purpose no-reference (NR) image quality assessment (IQA) model. The new approach, here called M1, competes with the Curvelet Quality Assessment proposed in 2014 (Curvelet2014). The central idea is to use descriptors based on robust statistics to extract features and predict the human opinion about degraded images. To show the consistency of the method the model is tested with 3 different datasets, LIVE IQA, TID2013 and CSIQ. To test evaluation, it is used the Wilcoxon test to verify the statistical significance of resu…
Tianjin University（天津大学）；City University of Hong Kong（香港城市大学）；Nanyang Technological University（南洋理工大学）；Beijing Jiaotong University（北京交通大学）
The 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 unpaired data during training. This is achieved…
No-reference image quality assessment (NR-IQA) aims to measure the image quality without reference image. However, contrast distortion has been overlooked in the current research of NR-IQA. In this paper, we propose a very simple but effective metric for predicting quality of contrast-altered images based on the fact that a high-contrast image is often more similar to its contrast enhanced image. Specifically, we first generate an enhanced image through histogram equalization. We then calculate the similarity of the original image and the enhanced one by using structural-similarity index (SSIM…
In this paper, we consider the problem of reference-based video super-resolution(RefVSR), i.e., how to utilize a high-resolution (HR) reference frame to super-resolve a low-resolution (LR) video sequence. The existing approaches to RefVSR essentially attempt to align the reference and the input sequence, in the presence of resolution gap and long temporal range. However, they either ignore temporal structure within the input sequence, or suffer accumulative alignment errors. To address these issues, we propose EFENet to exploit simultaneously the visual cues contained in the HR reference and t…
Self-Reference Deep Adaptive Curve Estimation for Low-Light Image Enhancement
Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））；Maynooth International Engineering College（梅努斯国际工程学院）；National University of Ireland Maynooth（爱尔兰国立梅努斯大学）；Southern University of Science and Technology（南方科技大学）；Northeastern University（东北大学）；NODAR Inc.（NODAR公司）
Gabor filters play an important role in many application areas for the enhancement of various types of images and the extraction of Gabor features. For the purpose of enhancing curved structures in noisy images, we introduce curved Gabor filters which locally adapt their shape to the direction of flow. These curved Gabor filters enable the choice of filter parameters which increase the smoothing power without creating artifacts in the enhanced image. In this paper, curved Gabor filters are applied to the curved ridge and valley structure of low-quality fingerprint images. First, we combine two…
Beijing University of Technology（北京工业大学）；University of Sydney（悉尼大学）；Nanyang Technological University（南洋理工大学）
In this paper we investigate into the problem of image quality assessment (IQA) and enhancement via machine learning. This issue has long attracted a wide range of attention in computational intelligence and image processing communities, since, for many practical applications, e.g. object detection and recognition, raw images are usually needed to be appropriately enhanced to raise the visual quality (e.g. visibility and contrast). In fact, proper enhancement can noticeably improve the quality of input images, even better than originally captured images which are generally thought to be of the…
Learning a typical image enhancement pipeline involves minimization of a loss function between enhanced and reference images. While L1 and L2 losses are perhaps the most widely used functions for this purpose, they do not necessarily lead to perceptually compelling results. In this paper, we show that adding a learned no-reference image quality metric to the loss can significantly improve enhancement operators. This metric is implemented using a CNN (convolutional neural network) trained on a large-scale dataset labelled with aesthetic preferences of human raters. This loss allows us to conven…
A main challenge faced in the deep learning-based Underwater Image Enhancement (UIE) is that the ground truth high-quality image is unavailable. Most of the existing methods first generate approximate reference maps and then train an enhancement network with certainty. This kind of method fails to handle the ambiguity of the reference map. In this paper, we resolve UIE into distribution estimation and consensus process. We present a novel probabilistic network to learn the enhancement distribution of degraded underwater images. Specifically, we combine conditional variational autoencoder with …
University of Tsukuba（筑波大学）；Waseda University（早稻田大学）；JST PRESTO（日本科学技术振兴机构 PRESTO 计划）
The remastering of vintage film comprises of a diversity of sub-tasks including super-resolution, noise removal, and contrast enhancement which aim to restore the deteriorated film medium to its original state. Additionally, due to the technical limitations of the time, most vintage film is either recorded in black and white, or has low quality colors, for which colorization becomes necessary. In this work, we propose a single framework to tackle the entire remastering task semi-interactively. Our work is based on temporal convolutional neural networks with attention mechanisms trained on vide…
Low light images suffer from severe noise, low brightness, low contrast, etc. In previous researches, many image enhancement methods have been proposed, but few methods can deal with these problems simultaneously. In this paper, to solve these problems simultaneously, we propose a low light image enhancement method that can combined with supervised learning and previous HSV (Hue, Saturation, Value) or Retinex model based image enhancement methods. First, we analyse the relationship between the HSV color space and the Retinex theory, and show that the V channel (V channel in HSV color space, eq…
Beijing University of Posts and Telecommunications（北京邮电大学）
It is suggested that low-light image enhancement realizes one-to-many mapping since we have different definitions of NORMAL-light given application scenarios or users' aesthetic. However, most existing methods ignore subjectivity of the task, and simply produce one result with fixed brightness. This paper proposes a neural network for multi-level low-light image enhancement, which is user-friendly to meet various requirements by selecting different images as brightness reference. Inspired by style transfer, our method decomposes an image into two low-coupling feature components in the latent s…
University of Science and Technology of China（中国科学技术大学）
Low-light image enhancement is an inherently subjective process whose targets vary with the user's aesthetic. Motivated by this, several personalized enhancement methods have been investigated. However, the enhancement process based on user preferences in these techniques is invisible, i.e., a "black box". In this work, we propose an intelligible unsupervised personalized enhancer (iUPEnhancer) for low-light images, which establishes the correlations between the low-light and the unpaired reference images with regard to three user-friendly attributions (brightness, chromaticity, and noise). Th…
JP Morgan Chase & Co.（摩根大通公司）；Huawei Noah’s Ark Lab（华为诺亚方舟实验室）；Queen Mary University of London（伦敦玛丽女王大学）
We present a novel approach to adjust global image properties such as colour, saturation, and luminance using human-interpretable image enhancement curves, inspired by the Photoshop curves tool. Our method, dubbed neural CURve Layers (CURL), is designed as a multi-colour space neural retouching block trained jointly in three different colour spaces (HSV, CIELab, RGB) guided by a novel multi-colour space loss. The curves are fully differentiable and are trained end-to-end for different computer vision problems including photo enhancement (RGB-to-RGB) and as part of the image signal processing p…
A Multi-Scale Spatial Attention-Based Zero-Shot Learning Framework for Low-Light Image Enhancement
School of Information Engineering, Xi’an Eurasia University, Xi’an, 710065, Shaanxi, China（西安欧亚大学信息工程学院）；Department of Electrical Engineering, University of Engineering and Technology Lahore（拉合尔工程与技术大学电气工程系）；Department of Computer Science, University of Engineering and Technology Lahore（拉合尔工程与技术大学计算机科学系）
Zero-Shot Video Restoration and Enhancement with Text-to-Image Latent Diffusion Models and Multi-Modal References
School of Electrical and Information Engineering, Tianjin University（天津大学电气自动化与信息工程学院）；Lappeenranta-Lahti University of Technology LUT（拉彭兰塔-拉赫蒂理工大学（LUT））
This paper presents a new method, called FlexiCurve, for photo enhancement. Unlike most existing methods that perform image-to-image mapping, which requires expensive pixel-wise reconstruction, FlexiCurve takes an input image and estimates global curves to adjust the image. The adjustment curves are specially designed for performing piecewise mapping, taking nonlinear adjustment and differentiability into account. To cope with challenging and diverse illumination properties in real-world images, FlexiCurve is formulated as a multi-task framework to produce diverse estimations and the associate…
Lunit Inc.（Lunit公司）；Adobe Research（Adobe研究院）；Korea Advanced Institute of Science and Technology (KAIST)（韩国科学技术院）
Learning-based color enhancement approaches typically learn to map from input images to retouched images. Most of existing methods require expensive pairs of input-retouched images or produce results in a non-interpretable way. In this paper, we present a deep reinforcement learning (DRL) based method for color enhancement to explicitly model the step-wise nature of human retouching process. We cast a color enhancement process as a Markov Decision Process where actions are defined as global color adjustment operations. Then we train our agent to learn the optimal global enhancement sequence of…
Low light conditions not only degrade human visual experience, but also reduce the performance of downstream machine analytics. Although many works have been designed for low-light enhancement or domain adaptive machine analytics, the former considers less on high-level vision, while the latter neglects the potential of image-level signal adjustment. How to restore underexposed images/videos from the perspective of machine vision has long been overlooked. In this paper, we are the first to propose a learnable illumination enhancement model for high-level vision. Inspired by real camera respons…
Anna University（安娜大学）；Nandha Engineering College（南达工程学院）
One of the important evidence in a crime scene that is normally overlooked but very important evidence is shoe print as the criminal is normally unaware of the mask for this. In this paper we use image processing technique to process reference shoe images to make it index-able for a search from the database the shoe print impressions available in the commercial market. This is achieved first by converting the commercially available image through the process of converting them to gray scale then apply image enhancement and restoration techniques and finally do image segmentation to store the se…
Recently, deep learning approaches have become the main research frontier for biological image reconstruction and enhancement problems thanks to their high performance, along with their ultra-fast inference times. However, due to the difficulty of obtaining matched reference data for supervised learning, there has been increasing interest in unsupervised learning approaches that do not need paired reference data. In particular, self-supervised learning and generative models have been successfully used for various biological imaging applications. In this paper, we overview these approaches from…
