本文提出了一种受物理学启发的对比学习范式用于低光照增强，称为PIE。PIE主要解决三个问题：（i）为解决现有基于学习的方法常使用严格像素对应图像对训练LLE模型的问题，我们消除了对像素对应配对训练数据的需求，转而使用非配对图像进行训练。（ii）针对现有方法忽视负样本且负样本生成不充分的问题，我们将受物理学启发的对比学习引入LLE，并设计了Bag of Curves（BoC）方法，以生成更合理、紧密遵循底层物理成像原理的负样本。（iii）为克服现有方法对语义真值的依赖，我们提出了一个无监督区域分割模块，在确保区域亮度一致性的同时消除对语义真值的依赖。总体而言，所提出的PIE能够有效地从非配对正/负样本中学习，并顺利实现非语义区域增强，这与现有LLE工作有明显区别。除了PIE的新颖架构外，我们还探究了PIE在语义分割和人脸检测等下游任务上的增益。在易于获取的开放数据上进行的训练以及大量实验表明，我们的方法在六个独立跨场景数据集上超越了最先进的LLE模型。PIE在测试时运行速度快且GFLOPs合理，便于在移动设备上使用。
英文摘要：
In this paper, we propose a physics-inspired contrastive learning paradigm for low-light enhancement, called PIE. PIE primarily addresses three issues: (i) To resolve the problem of existing learning-based methods often training a LLE model with strict pixel-correspondence image pairs, we eliminate the need for pixel-correspondence paired training data and instead train with unpaired images. (ii) To address the disregard for negative samples and the inadequacy of their generation in existing methods, we incorporate physics-inspired contrastive learning for LLE and design the Bag of Curves (BoC) method to generate more reasonable negative samples that closely adhere to the underlying physical imaging principle. (iii) To overcome the reliance on semantic ground truths in existing methods, we propose an unsupervised regional segmentation module, ensuring regional brightness consistency while eliminating the dependency on semantic ground truths. Overall, the proposed PIE can effectively learn from unpaired positive/negative samples and smoothly realize non-semantic regional enhancement, which is clearly different from existing LLE efforts. Besides the novel architecture of PIE, we explore the gain of PIE on downstream tasks such as semantic segmentation and face detection. Training on readily available open data and extensive experiments demonstrate that our method surpasses the state-of-the-art LLE models over six independent cross-scenes datasets. PIE runs fast with reasonable GFLOPs in test time, making it easy to use on mobile devices.
A Perceptually Inspired Variational Framework for Color Enhancement
Department of Electrical Engineering, Universidad de Chile（智利大学电气工程系）；Dipartimento di Tecnologia dell’Informazione, Università di Milano（米兰大学信息科技技术系）；Departament de Tecnologia, Universitat Pompeu Fabra（庞培法布拉大学技术系）
School of Computer Science and Technology, Beijing Institute of Technology（计算机科学与技术学院，北京理工大学）；School of Artificial Intelligence, Beijing Normal University（人工智能学院，北京师范大学）
PHISWID: Physics-Inspired Underwater Image Dataset Synthesized from RGB-D Images
Graduate School of Engineering, The University of Osaka（大阪大学工学研究科）；Graduate School of BASE, Tokyo University of Agriculture and Technology（东京大学农业技术大学院大学）
Downstream Task Inspired Underwater Image Enhancement: A Perception-Aware Study from Dataset Construction to Network Design
State Key Laboratory of Physical Oceanography, Ocean University of China（中国海洋大学物理海洋国家重点实验室）；Department of Electrical and Computer Engineering, Mississippi State University（密苏里州立大学电子与计算机工程系）
Cognition-Inspired Dual-Stream Semantic Enhancement for Vision-Based Dynamic Emotion Modeling
College of Intelligent Robotics and Advanced Manufacturing, Fudan University（复旦大学智能机器人与先进制造学院）；Shanghai Key Lab of Intelligent Information Processing, College of Computer Science and Artificial Intelligence, Fudan University（上海智能信息处理重点实验室，复旦大学计算机科学与人工智能学院）；School of Data Science and Engineering, East China Normal University（华东师范大学数据科学与工程学院）
