Low-Light Video Enhancement with An Effective Spatial-Temporal Decomposition Paradigm
Department of Computer Science and Engineering, The Chinese University of Hong Kong（计算机科学与工程系，香港中文大学）；Shenzhen University（深圳大学）；The University of Hong Kong（香港大学）；camera group of DJI（大疆创新相机组）；Zhejiang Normal University（浙江师范大学）
Xiaogang Xu, Kun Zhou, Tao Hu, Jiafei Wu, Ruixing Wang, Hao Peng, Bei Yu
Low-Light Video Enhancement (LLVE) seeks to restore dynamic or static scenes plagued by severe invisibility and noise. In this paper, we present an innovative video decomposition strategy that incorporates view-independent and view-dependent components to enhance the performance of LLVE. The framework is called View-aware Low-light Video Enhancement (VLLVE). We leverage dynamic cross-frame correspondences for the view-independent term (which primarily captures intrinsic appearance) and impose a scene-level continuity constraint on the view-dependent term (which mainly describes the shading condition) to achieve consistent and satisfactory decomposition results. To further ensure consistent decomposition, we introduce a dual-structure enhancement network featuring a cross-frame interaction mechanism. By supervising different frames simultaneously, this network encourages them to exhibit matching decomposition features. This mechanism can seamlessly integrate with encoder-decoder single-frame networks, incurring minimal additional parameter costs. Building upon VLLVE, we propose a more comprehensive decomposition strategy by introducing an additive residual term, resulting in VLLVE++. This residual term can simulate scene-adaptive degradations, which are difficult to model using a decomposition formulation for common scenes, thereby further enhancing the ability to capture the overall content of videos. In addition, VLLVE++ enables bidirectional learning for both enhancement and degradation-aware correspondence refinement (end-to-end manner), effectively increasing reliable correspondences while filtering out incorrect ones. Notably, VLLVE++ demonstrates strong capability in handling challenging cases, such as real-world scenes and videos with high dynamics. Extensive experiments are conducted on widely recognized LLVE benchmarks.
Low-light Image Enhancement with Retinex Decomposition in Latent Space
School of Automation, Hangzhou Dianzi University（杭州电子科技大学自动化学院）；College of Artificial Intelligence, Jiaxing University（嘉兴大学人工智能学院）；School of Artificial Intelligence at Dalian University of Technology（大连理工大学人工智能学院）；Department of Computer Science at City University of Hong Kong（香港城市大学计算机科学系）
Joint RGB-Spectral Decomposition Model Guided Image Enhancement in Mobile Photography
School of Electronic Science and Engineering, Nanjing University（南京大学电子科学与工程学院）；Nanyang Technological University（南洋理工大学）；Key Laboratory of Optoelectronic Devices and Systems with Extreme Performances of MOE, Nanjing University（南京大学极端性能光电器件与系统教育部重点实验室）
Low-Light Video Enhancement via Spatial-Temporal Consistent Decomposition
The Chinese University of Hong Kong（香港中文大学）；Zhejiang University（浙江大学）；The Chinese University of Hong Kong (Shenzhen)（香港中文大学（深圳））；PICO, Bytedance（字节跳动PICO）；The University of Hong Kong（香港大学）；DJI Technology Co., Ltd.（大疆科技有限公司）；Zhejiang Normal University（浙江师范大学）
IllumFlow: Illumination-Adaptive Low-Light Enhancement via Conditional Rectified Flow and Retinex Decomposition
School of Mathematics and Statistics, Xidian University（西安电子科技大学数学与统计学学院）；School of Mathematics and Statistics, Xi'an Jiaotong University（西安交通大学数学与统计学学院）
When Integral Meets Decomposition: A Signal-Level Self-Supervised Feature Decompose Paradigm for Multi-Modal Image Fusion
College of Computer Science and Engineering, Dalian Minzu University（大连民族大学计算机科学与工程学院）；School of Artificial Intelligence and Robotics, Hunan University（湖南大学人工智能与机器人学院）；Department of Automation, Tsinghua University（清华大学自动化系）
Underwater Organism Color Enhancement via Color Code Decomposition, Adaptation and Interpolation
School of Cyber Science and Engineering, Southeast University（东南大学网络空间科学与工程学院）；School of Computer Science, The University of Sydney（悉尼大学计算机科学学院）；National University of Singapore（新加坡国立大学）；School of Information Science and Engineering, Southeast University（东南大学信息科学与工程学院）；Purple Mountain Laboratories（紫金山实验室）；Department of Computer Science and Engineering, The Hong Kong University of Science and Technology（香港科技大学计算机科学与工程学系）；Department of Computer and Information Science, University of Macau（澳门大学计算机与信息科学系）
Bracketing Image Restoration and Enhancement with High-Low Frequency Decomposition
Xi’an University of Architecture and Technology（西安建筑科技大学）；Northwestern Polytechnical University（西北工业大学）；University of Macau（澳门大学）；Xi’an Institute of Optics and Precision Mechanics of CAS（中国科学院西安光学精密机械研究所）
Lightweight and Fast Real-time Image Enhancement via Decomposition of the Spatial-aware Lookup Tables
IPAI, Seoul National University, Seoul, Korea（IPAI，首尔国立大学，首尔，韩国）；LG Electronics, Seoul, Korea（LG电子，首尔，韩国）；Department of ECE, INMC, Seoul National University, Seoul, Korea（电子工程系，INMC，首尔国立大学，首尔，韩国）
Excavate the potential of Single-Scale Features: A Decomposition Network for Water-Related Optical Image Enhancement
College of Computer Science & Technology, Qingdao University（青岛大学计算机科学与技术学院）；College of Computer and Data Science, Fuzhou University（福州大学计算机与数据科学学院）；School of Computing and Mathematical Sciences, University of Leicester（莱斯特大学计算与数学科学学院）；School of Computer Science, University of Birmingham（伯明翰大学计算机科学学院）；Department of Computational Engineering, Lappeenranta-Lahti University of Technology (LUT), and Atmospheric Modelling Centre-Lahti（拉佩兰塔-拉赫蒂技术大学（LUT）计算工程系及拉赫蒂大气建模中心）；Computer Science Department, University of Exeter（埃克塞特大学计算机科学系）；Computer Science and Technology at Shandong Technology and Business University（山东科技职业大学计算机科学与技术）
A Coupling Enhancement Algorithm for ZrO2 Ceramic Bearing Ball Surface Defect Detection Based on Cartoon-texture Decomposition Model and Multi-Scale Filtering Method
Di$^2$CycleSB: Towards High-Quality Unsupervised Nighttime Visibility Enhancement via Schrödinger Bridge Transformer
Faculty of Data Science, City University of Macau（澳门城市大学数据科学学院）；Department of Automation, Tsinghua University（清华大学自动化系）；College of Computer Science and Software Engineering, Shenzhen University（深圳大学计算机与软件学院）
Compressed Video Quality Enhancement: Classifying and Benchmarking over Standards
Faculty of Electronics and Telecommunications, VNU University of Engineering and Technology（电子与电信学院，越南工程大学）；Department of Computer Science, National Yang Ming Chiao Tung University（计算机科学系，国家阳明交通大学）
LightenDiffusion: Unsupervised Low-Light Image Enhancement with Latent-Retinex Diffusion Models
Shanghai Jiao Tong University（上海交通大学）；Megvii Technology（旷视科技）；Sichuan University（四川大学）；Southwest Jiaotong University（西南交通大学）；University of Electronic Science and Technology of China（电子科技大学）
Nanjing University of Aeronautics and Astronautics（南京航空航天大学）；MIIT Key Laboratory of Pattern Analysis and Machine Intelligence（工业和信息化部模式分析与机器智能重点实验室）；Collaborative Innovation Center of Novel Software Technology and Industrialization（新型软件技术与产业化协同创新中心）
Information-Theoretic Decomposition for Multimodal Interaction Learning
Gaoling School of Artificial Intelligence, Renmin University of China, Beijing（中国人民大学人工智能学院，北京）；Beijing Key Laboratory of Research on Large Models（北京大模型研究关键实验室）；Engineering Research Center of Next-Generation Intelligent Search（下一代智能搜索与推荐工程研究中心）；Beihang University, Beijing（北航，北京）；Gaotu Techedu Inc.（高图科技有限公司）
DA-DRN: Degradation-Aware Deep Retinex Network for Low-Light Image Enhancement
MOE Key Lab for Neuroinformation, University of Electronic Science and Technology of China (UESTC)（电子科技大学神经信息教育部重点实验室（UESTC））；University of Electronic Science and Technology of China (UESTC)（电子科技大学（UESTC））
在真实世界的低光条件下获得的图像不仅亮度低，而且还遭受许多其他类型的退化，例如颜色失真，未知噪声，细节丢失和光晕伪影。在本文中，我们提出了一种用于弱光图像增强的Degradation-Aware Deep Retinex Network（DA-DRN），并解决了上述退化问题。基于Retinex理论，该模型中的分解网络可以将低光照图像分解为反射率图和光照图，并直接处理分解阶段反射率的退化。我们提出了一个退化感知模块（DA模块），它可以指导分解器的训练过程，并使分解器在训练阶段是一个恢复器，而无需在测试阶段增加额外的计算成本。DA模块可以实现去除噪声的目的，同时将细节信息保留到光照图中，并解决颜色失真和光晕伪影。我们引入感知损失来训练增强网络，以生成更符合人类视觉感知的亮度改进的照明图。我们训练和评估我们提出的模型在LOL真实世界和LOL合成数据集上的性能，我们还测试了我们的模型在其他几个常用的数据集没有地面真理（LIME，DICM，MEF和NPE数据集）。我们进行了大量的实验，以证明我们的方法取得了良好的鲁棒性和泛化效果，并优于许多其他国家的最先进的方法定性和定量。我们的方法只需要7毫秒处理一个图像与600 x400分辨率上的TITAN Xp GPU。
