arXiv 2101.080392021-01-20eess.IVcs.CVcs.LG

Bridge the Vision Gap from Field to Command: A Deep Learning Network Enhancing Illumination and Details

Beijing University of Posts and Telecommunications（北京邮电大学）；Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）

Zhuqing Jiang, Chang Liu, Ya'nan Wang, Kai Li, Aidong Men, Haiying Wang, Haiyong Luo

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

英文摘要相关论文

英文摘要：

With the goal of tuning up the brightness, low-light image enhancement enjoys numerous applications, such as surveillance, remote sensing and computational photography. Images captured under low-light conditions often suffer from poor visibility and blur. Solely brightening the dark regions will inevitably amplify the blur, thus may lead to detail loss. In this paper, we propose a simple yet effective two-stream framework named NEID to tune up the brightness and enhance the details simultaneously without introducing many computational costs. Precisely, the proposed method consists of three parts: Light Enhancement (LE), Detail Refinement (DR) and Feature Fusing (FF) module, which can aggregate composite features oriented to multiple tasks based on channel attention mechanism. Extensive experiments conducted on several benchmark datasets demonstrate the efficacy of our method and its superiority over state-of-the-art methods.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

数据相对不确定性框架用于低光照动漫场景图像增强

Data relativistic uncertainty framework for low-illumination anime scenery image enhancement

Heriot-Watt University（赫瑞瓦特大学）

本文提出DRU框架，通过引入数据相对不确定性解决动漫场景低光照增强问题，提升图像感知和审美质量。

2026-03-11cs.CVcs.LGcs.MM

基于退化感知混合专家增强的低光照无人机图像桥梁损伤检测

Bridge Damage Detection from Low-Light UAV Imagery via Degradation-Aware Mixture-of-Experts Enhancement

School of Computer Science and Engineering, University of Electronic Science and Technology of China（电子科技大学计算机科学与工程学院）；Sustainability X-Lab, The University of Hong Kong（香港大学可持续发展X实验室）；School of Architecture, Building, and Civil Engineering, Loughborough University（拉夫堡大学建筑、建造与土木工程学院）；Department of Engineering Science, University of Oxford（牛津大学工程科学系）；Department of Civil and Environmental Engineering, The Hong Kong University of Science and Technology（香港科技大学土木与环境工程系）

针对低光照无人机桥梁图像缺陷模糊问题，提出DaL-MoE退化感知混合专家恢复前端，提升了YOLOv11m的桥梁损伤检测精度，实现了合成退化到真实场景的性能迁移。

2026-08-25cs.CV

Meta-learning Convolutional Neural Architectures for Multi-target Concrete Defect Classification with the COncrete DEfect BRidge IMage Dataset

Goethe University（歌德大学）；Egnatia Odos A. E.（埃格纳蒂亚公路公司）

Recognition of defects in concrete infrastructure, especially in bridges, is a costly and time consuming crucial first step in the assessment of the structural integrity. Large variation in appearance of the concrete material, changing illumination and weather conditions, a variety of possible surface markings as well as the possibility for different types of defects to overlap, make it a challenging real-world task. In this work we introduce the novel COncrete DEfect BRidge IMage dataset (CODEBRIM) for multi-target classification of five commonly appearing concrete defects. We investigate and…

2019-04-02cs.CVcs.LGstat.ML

面向可控低光照图像增强：一个连续多光照数据集和高效状态空间框架

Towards Controllable Low-Light Image Enhancement: A Continuous Multi-illumination Dataset and Efficient State Space Framework

Department of Computer and Information Science, University of Macau（澳门大学计算机与信息科学系）；School of Automation, China University of Geosciences（中国地质大学自动化学院）；Department of Electromechanical Engineering, University of Macau（澳门大学机电工程系）

本文提出可控低光照增强(CLE)方法，通过引入CLE-RWKV框架和Light100数据集，解决低光照图像增强中的亮度控制与色度保真冲突问题，提升增强效果的可控性和鲁棒性。

2026-03-26cs.CV

基于物理四元先验的零参考低光照增强

Zero-Reference Low-Light Enhancement via Physical Quadruple Priors

Peking University（北京大学）；Microsoft Research Asia（微软亚洲研究院）

本文提出一种基于物理光传输理论光照不变先验的零参考低光照增强框架，仅需正常光照图像训练，利用预训练扩散模型和旁路解码器实现高效、鲁棒且具可解释性的图像恢复。

2024-03-19cs.CV

Learning Deep Context-Sensitive Decomposition for Low-Light Image Enhancement

Dalian University of Technology（大连理工大学）；Peng Cheng Laboratory（鹏城实验室）

Enhancing the quality of low-light images plays a very important role in many image processing and multimedia applications. In recent years, a variety of deep learning techniques have been developed to address this challenging task. A typical framework is to simultaneously estimate the illumination and reflectance, but they disregard the scene-level contextual information encapsulated in feature spaces, causing many unfavorable outcomes, e.g., details loss, color unsaturation, artifacts, and so on. To address these issues, we develop a new context-sensitive decomposition network architecture t…

2021-12-09cs.CVeess.IV

更多相关论文收起更多论文

Mask2Real-WM：作为可控灵巧世界模型的模拟到现实桥梁的分割掩码

Mask2Real-WM: Controllable Dexterous World Models via Segmentation Masks as a Sim-to-Real Bridge

Soft Robotic Lab, Department of Mechanical and Process Engineering ETH Zurich, Switzerland（苏黎世联邦理工学院机械与过程工程系软机器人实验室）

提出Mask2Real-WM，一种用于灵巧操纵的两阶段动作条件世界模型，将像素预测解耦为动力学和渲染模型，利用分割空间较小的模拟到现实差距，通过合成数据预训练和真实演示微调实现各自由度动作可控。

2026-10-06cs.AIcs.CVcs.LG

基于物理信息神经网络的高速视频熔池流场重建

Reconstruction of Molten Pool Flow Fields from High-Speed Video Using Physics-Informed Neural Networks

University of Kentucky（肯塔基大学）；Hanoi University of Industry（河内工业大学）

本研究利用物理信息神经网络从高速视频重建丝材-电弧DED熔池表面流场，结合光流与流体方程，实现准稳态和周期性冲击下的物理约束流场诊断。

2026-09-29eess.IVphysics.flu-dyn

在轨6D位姿估计的领域泛化

Domain Generalization for In-Orbit 6D Pose Estimation

UCLouvain, ICTEAM, Dept. Electrical Engineering（UCLouvain 信息与通信技术团队，电气工程系）；KU Leuven, Dept. Electrical Engineering（库尔勒大学电气工程系）；KU Leuven, Dept. Mechanical Engineering（库尔勒大学机械工程系）

针对在轨航天器6D位姿估计中合成图像与真实图像间的领域差距问题，提出一种结合端到端神经架构、多任务学习和数据增强的新方法，在SPEED+数据集上达到最先进精度。

2025-09-18cs.CVeess.IV