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 videos with data-driven deterioration simulation. Our proposed source-reference attention allows the model to handle an arbitrary number of reference color images to colorize long videos without the need for segmentation while maintaining temporal consistency. Quantitative analysis shows that our framework outperforms existing approaches, and that, in contrast to existing approaches, the performance of our framework increases with longer videos and more reference color images.
Better Than Reference In Low Light Image Enhancement: Conditional Re-Enhancement Networks
Harbin Institute of Technology(哈尔滨工业大学)
弱光图像存在噪声严重、亮度低、对比度低等问题。在以往的研究中,提出了许多图像增强方法,但很少有方法能同时处理这些问题。针对这些问题,本文提出了一种结合监督学习和以往基于HSV(Hue,Saturation,Value)或Retinex模型的图像增强方法的弱光图像增强方法。首先,分析了HSV颜色空间与Retinex理论的关系,证明了增强图像的V通道(HSV颜色空间中的V通道,等于RGB颜色空间中的最大通道)能够很好地表征对比度和亮度增强过程。然后,提出了一种数据驱动的条件再增强网络(表示为CRENet)。该网络以弱光图像为输入,以增强后的V通道为条件,重新增强弱光图像的对比度和亮度,同时降低噪声和色彩失真。需要注意的是,在训练过程中,任何曝光时间不同的配对图像都可以用于训练,不需要仔细选择监督图像,这会节省很多。此外,在2080 Ti GPU上处理分辨率为400*600的彩色图像所需时间不到20 ms。最后通过对比实验验证了该方法的有效性。实验结果表明,本文提出的方法能够显著提高增强后图像的质量,并且通过与其他图像对比度增强方法相结合,最终增强结果甚至可以在对比度和亮度上优于参考图像。(Code将在https://github.com/hitzhangyu/image-enhancement-with-denoise上提供)
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)
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)
Comprehensive evaluation of no-reference image quality assessment algorithms on authentic distortions
客观图像质量评价是对数字图像感知质量的预测。无参考图像质量评估预测给定输入图像的质量,而不需要关于其原始(无失真)对应物的任何知识或信息。机器学习算法在无参考图像质量评估中被大量使用,因为它是非常复杂的人类视觉系统的质量感知建模。此外,无参考图像质量评估算法进行评估,公开可用的基准数据库。这些数据库包含具有相应质量分数的图像。在这项研究中,我们评估了几个基于机器学习的NR-IQA方法和一个意见不知情的方法对数据库组成的真实失真。具体而言,LIVE In the Wild和KonIQ-10 k数据库被应用于评估最先进的。80%用于培训,其余20%用于测试。此外,平均PLCC,SROCC和KROCC值报告超过100个随机训练测试分裂。PLCC、SROCC和KROCC值的统计数据也使用箱形图发布。我们的评估结果可能有助于获得一个清晰的了解国家的最先进的无参考图像质量评估方法的地位。
A Comprehensive Survey on Underwater Image Enhancement Based on Deep Learning
School of Cyber Science and Engineering, Southeast University(东南大学计算机科学与工程学院);Purple Mountain Laboratories(紫金山实验室);Engineering Research Center of Blockchain Application, Supervision And Management (Southeast University)(区块链应用、监督与管理工程研究中心(东南大学));State Key Laboratory of Millimeter Waves, School of Information Science and Engineering, Southeast University(毫米波国家重点实验室,信息科学与工程学院,东南大学);College of Computing & Data Science at Nanyang Technological University(南洋理工大学计算与数据科学学院)
An Underwater Image Enhancement Benchmark Dataset and Beyond
City University of Hong Kong(香港城市大学);Institute of Information Engineering, Chinese Academy of Sciences(中国科学院信息工程研究所);Tianjin University(天津大学);Beijing Jiaotong University(北京交通大学)
A Generative Data Framework with Authentic Supervision for Underwater Image Restoration and Enhancement
Institute of Artificial Intelligence (TeleAI), China Telecom(人工智能研究院(TeleAI),中国电信);Department of Automation, Shanghai Jiao Tong University(自动化系,上海交通大学);School of Artificial Intelligence, Optics and ElectroNics (iOPEN), Northwestern Polytechnical University(人工智能、光学与电子学学院(iOPEN),西北工业大学);Xi’an Institute of Optics and Precision Mechanics, Chinese Academy of Sciences(西安光学精密机械研究所,中国科学院)
UIEDP:Underwater Image Enhancement with Diffusion Prior
Beihang University(北京航空航天大学);Hangzhou Innovation Institute, Beihang University(北京航空航天大学杭州创新研究院);University of Chinese Academy of Sciences(中国科学院大学);Tsinghua University(清华大学)
Diffusion Models for Image Restoration and Enhancement: A Comprehensive Survey
University of Science and Technology of China(科学技术大学);National University of Singapore(国立新加坡大学);Eastern Institute for Advanced Study(东部高级研究机构);Microsoft Research Asia(微软亚洲研究院)
Burstormer: Burst Image Restoration and Enhancement Transformer
Mohamed bin Zayed University of AI(穆罕默德·本·扎耶德人工智能大学);Inception Institute of AI(Inception人工智能研究院);Australian National University(澳大利亚国立大学);Linköping University(林雪平大学);University of California, Merced(加州大学默塞德分校);Yonsei University(延世大学);Google Research(谷歌研究院)
Sliced Maximal Information Coefficient: A Training-Free Approach for Image Quality Assessment Enhancement
Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ)(广东省人工智能与数字经济实验室(深圳));College of Computer Science and Software Engineering, Shenzhen University(深圳大学计算机与软件学院);School Of Computer Science, South China Normal University(华南师范大学计算机学院)
End-To-End Underwater Video Enhancement: Dataset and Model
Hangzhou Innovation Institute, Beihang University(北京航空航天大学杭州创新研究院);Institute of Software, Chinese Academy of Science(中国科学院软件研究所);University of Chinese Academy of Sciences(中国科学院大学)