Nighttime image dehazing via a physics-aware dynamic neural model with progressive contrastive regularization
Authors:
- Yun LiangYLYun Liang
- Xinjie XiaoXXXinjie Xiao
- Zihan ZhouZZZihan Zhou
- Lianghui LiLLLianghui Li
- Yuhui QuanYQYuhui Quan
- 30 May 2025
- journal article
- Published by Elsevier in Pattern Recognition
- Vol. 169
Abstract
No abstract availableFunding Information
- National Natural Science Foundation of China (62401210)
- National Key Research and Development Program of China (2024YFC2814901)
- Southern Marine Science and Engineering Guangdong Laboratory (ZJW-2023-04)
- Guangdong Provincial Natural Science Foundation (2025A1515011539)
- Key Technologies Research and Development Program of Guangzhou Municipality (202206010091)
- Basic and Applied Basic Research Foundation of Guangdong Province (2023A1515110646)
- Science and Technology Planning Project of Guangdong Province
This publication has 26 references indexed in Scilit:
- Dual-path dehazing network with spatial-frequency feature fusionPattern Recognition, 2024
- Restoring vision in hazy weather with hierarchical contrastive learningPattern Recognition, 2023
- Curricular Contrastive Regularization for Physics-Aware Single Image Dehazing2023
- Single nighttime image dehazing based on unified variational decomposition model and multi-scale contrast enhancementEngineering Applications of Artificial Intelligence, 2022
- Rapid nighttime haze removal with color-gray layer decompositionSignal Processing, 2022
- Decoupled Dynamic Filter Networks2021
- Contrastive Learning for Compact Single Image Dehazing2021
- Single nighttime image dehazing based on image decompositionSignal Processing, 2021
- The Unreasonable Effectiveness of Deep Features as a Perceptual Metric2018
- Fast Haze Removal for Nighttime Image Using Maximum Reflectance Prior2017