基于深度学习的雾图生成算法综述-国际计算机科学进展-CSCIED科技核心评价数据库-手机版

基于深度学习的雾图生成算法综述

A review of fog image generation algorithms based on deep learning

ES评分 0 浏览量：45 下载量：0

DOI	10.12208/j.aics.20250052
刊名	国际计算机科学进展 Advances in International Computer Science
年，卷(期)	2025, 5(3)
作者	刘述民, 杨俊俊,
作者单位	江西理工大学软件工程学院江西南昌
摘要	雾图生成技术旨在将清晰图像合成为具有真实雾霾视觉效果的图像，是计算机视觉领域的重要研究方向。该技术不仅是增强图像去雾模型训练效果、提升视觉系统在复杂环境下鲁棒性的关键技术手段，还在自动驾驶仿真测试、影视特效制作、数字艺术创作等实际场景中展现出广泛应用价值。传统雾图生成方法高度依赖大气散射模型的参数估计，受限于模型简化性与参数设计主观性，生成雾图的真实感与场景适应性均存在明显不足。近年来，深度学习技术的快速发展，尤其是生成对抗网络与扩散模型的突破性应用，为雾图生成技术注入了新的发展动力。本文系统梳理了基于深度学习的雾图生成算法研究进展，将其划分为物理模型引导型、端到端生成型与扩散模型驱动型三大类别，深入剖析各类方法的核心原理、技术优势及适用局限。最后，结合当前研究现状，总结该领域面临的关键挑战，并从技术融合、功能拓展、性能优化等角度展望未来研究方向，为后续相关研究提供参考。
Abstract	Fog image generation technology aims to synthesize clear images into images with realistic foggy visual effects and is an important research direction in the field of computer vision. This technology is not only a key means to enhance the training effectiveness of image dehazing models and improve the robustness of visual systems in complex environments, but also demonstrates broad application value in practical scenarios such as autonomous driving simulation tests, film special effects production, and digital art creation. Traditional fog image generation methods rely heavily on parameter estimation of atmospheric scattering models. Due to the simplification of the models and the subjectivity in parameter design, both the realism and scene adaptability of the generated fog images are significantly limited. In recent years, the rapid development of deep learning technology, especially the breakthrough applications of generative adversarial networks and diffusion models, has injected new momentum into fog image generation technology. This paper systematically reviews the research progress of deep learning-based fog image generation algorithms, categorizing them into three major types: physics model-guided, end-to-end generation, and diffusion model-driven. It provides an in-depth analysis of the core principles, technical advantages, and applicable limitations of each type. Finally, in combination with the current research status, the paper summarizes the key challenges in this field and, from the perspectives of technology integration, functional expansion, and performance optimization, explores future research directions, providing a reference for subsequent related studies.
关键词	雾图生成；深度学习；生成对抗网络；扩散模型
KeyWord	Foggy image generation; Deep learning; Generative adversarial networks; Diffusion models
基金项目
页码	18-23

参考文献
相关文献

[1] Ian J. Goodfellow,Jean Pouget-Abadie,Mehdi Mirza,et al. Generative Adversarial Networks
[J]. Computer Science, 2014,.

[2] Muyang Li,Tianle Cai,Jiaxin Cao,et al. DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models
[J]. 2024,

[3] 刘勇. 基于深度学习的轻量化图像去雾算法研究
[D]. 电子科技大学,2022.

[4] 唐斌,陈清容,段春红. 基于大气散射模型的图像去雾及亮度增强算法
[J]. 光电子(激光),2024,35(3): 303-310.

[5] Cai, BL (Cai, Bolun),et al. DehazeNet: An End-to-End System for Single Image Haze Removal
[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2016, Vol.25(11): 5187-5198.

[6] 董永生,范世朝,张宇,等. 生成对抗网络的发展与挑战
[J]. 信号处理,2023,39(1): 154-175.

[7] Jun-Yan Zhu,Taesung Park,Phillip Isola,et al. Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
[J]. 2020,.

[8] Dongdong Lin,Benedetta Tondi,Bin Li,et al. A CycleGAN Watermarking Method for Ownership Verification
[J]. IEEE Transactions on Dependable and Secure Computing,2025, Vol.22(2): 1040-1054.

[9] Ziyu Cui,Zijun Wei,Xiaohui Yuan,et al. CGAN Accelerated Subdivision Surface BEM for Acoustic Scattering
[J]. CMES - Computer Modeling in Engineering and Sciences, 2025,Vol.144(1): 1045-1070.

[10] 孙子奇,曹战,陈华. 基于改进Pix2Pix的地质剖面生成方法
[J]. 科学技术与工程,2025,25(19): 8025-8033.

[11] Muhammad Asif Khan,Hamid Menouar,Ridha Hamila. Multimodal Crowd Counting with Pix2Pix GANs
[J]. 2024,.

[12] 苏彤,许杰. 基于生成对抗网络的树种识别方法
[J]. 林业科学, 2024,60(2): 97-105.

[13] 李响,严毅,刘明辉,等. 基于多条件对抗和梯度优化的生成对抗网络
[J]. 电子科技大学学报,2021,50(5): 754-760.

[14] 闫志浩,周长兵,李小翠. 生成扩散模型研究综述
[J]. 计算机科学,2024,51(1): 273-283.

[15] 郭璠,刘文韬,杨佳男,等. 基于半解析模型的夜间雾天图像生成算法
[J]. 通信学报,2025,46(4): 129-143.

[16] 叶文龙,陈斌. PanoLoRA：基于Stable Diffusion的全景图像生成的高效微调方法
[J]. 图学学报,2025,46(5): 980-989.

[17] 白少杰,林立霞,胡子寒,等. 基于LoRA 的双阶段扩散模型水印方案①
[J]. 计算机系统应用,2025,(6).

[18] 王铭,姜淑华,吴杰,等. 基于改进生成式对抗网络的图像去雾算法研究
[J]. 长春理工大学学报(自然科学版), 2021, 44(2): 93-99.

[19] 张弛,吴鑫,张建奇,等. 基于动态粒子参数选择的水雾透过率计算
[J]. 光学精密工程,2021,29(2): 231-242.

[20] 李思聪,王坚,宋亚飞,等. 基于扩散模型的恶意代码数据集扩充方法
[J]. 空军工程大学学报,2025,26(1): 95-103.

[21] 王铭,姜淑华,吴杰,等. 基于改进生成式对抗网络的图像去雾算法研究
[J]. 长春理工大学学报(自然科学版), 2021, 44(2): 93-99.

引用本文

刘述民, 杨俊俊. 基于深度学习的雾图生成算法综述 [J]. 国际计算机科学进展. 2025; 5; (3). 18 - 23.

文献评论

相关学者

相关机构