An Interpretable Image Denoising Framework via Dual Disentangled Representation Learning | |
Liang, Yunji6; Fan, Jiayuan6; Zheng, Xiaolong5; Wang, Yutong4; Huangfu, Luwen2,3; Ghavate, Vedant1; Yu, Zhiwen6 | |
刊名 | IEEE TRANSACTIONS ON INTELLIGENT VEHICLES |
2024 | |
卷号 | 9期号:1页码:2016-2030 |
关键词 | Meteorology Task analysis Image denoising Noise reduction Image restoration Semantics Robustness Dual disentangled representation adverse weather image denoising interpretability robustness |
ISSN号 | 2379-8858 |
DOI | 10.1109/TIV.2023.3331017 |
通讯作者 | Liang, Yunji(liangyunji@nwpu.edu.cn) |
英文摘要 | Various unfavourable conditions such as fog, snow and rain may degrade image quality and pose tremendous threats to the safety of autonomous driving. Numerous image-denoising solutions have been proposed to improve visibility under adverse weather conditions. However, previous studies have been limited in robustness, generalization ability, and interpretability as they were designed for specific scenarios. To address this problem, we introduce an interpretable image denoising framework via Dual Disentangled Representation Learning (DDRL) to enhance robustness and interpretability by decomposing an image into content factors (e.g., objects) and context factors (e.g., weather conditions). DDRL consists of two Disentangled Representation Learning (DRL) blocks. In each DRL block, an input image is deconstructed into the latent content distribution and the weather distribution by minimizing their mutual information. To mitigate the impacts of weather styles, we incorporated a content discriminator and adversarial objectives to learn the decomposable interaction between two DRL blocks. Furthermore, we standardized the weather feature space, enabling our method to be applicable to various downstream tasks such as diverse degraded image generation. We evaluated DDRL under three weather conditions including fog, rain, and snow. The experimental results demonstrate that DDRL shows competitive performance with good generalization capability and high robustness under numerous weather conditions. Furthermore, quantitative analysis shows that DDRL can capture interpretable variations of weather factors and decompose them for safe and reliable all-weather autonomous driving. |
资助项目 | Natural Science Foundation of China[62372378] ; Natural Science Foundation of China[72225011] |
WOS关键词 | WEATHER ; NETWORK ; SNOW ; RAIN |
WOS研究方向 | Computer Science ; Engineering ; Transportation |
语种 | 英语 |
出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
WOS记录号 | WOS:001173317800171 |
资助机构 | Natural Science Foundation of China |
内容类型 | 期刊论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/58695] |
专题 | 自动化研究所_复杂系统管理与控制国家重点实验室_先进控制与自动化团队 |
通讯作者 | Liang, Yunji |
作者单位 | 1.San Diego State Univ SDSU, Coll Arts & Letters, San Diego, CA 92182 USA 2.San Diego State Univ SDSU, Ctr Human Dynam Mobile Age HDMA, San Diego, CA 92182 USA 3.San Diego State Univ, Fowler Coll Business FCB, San Diego, CA 92182 USA 4.Chinese Acad Sci, Inst Automat, State Key Lab Multimodal Artificial Intelligence, Beijing 100190, Peoples R China 5.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Sys, Beijing 100190, Peoples R China 6.Northwestern Polytech Univ, Sch Comp Sci, Xian 710072, Peoples R China |
推荐引用方式 GB/T 7714 | Liang, Yunji,Fan, Jiayuan,Zheng, Xiaolong,et al. An Interpretable Image Denoising Framework via Dual Disentangled Representation Learning[J]. IEEE TRANSACTIONS ON INTELLIGENT VEHICLES,2024,9(1):2016-2030. |
APA | Liang, Yunji.,Fan, Jiayuan.,Zheng, Xiaolong.,Wang, Yutong.,Huangfu, Luwen.,...&Yu, Zhiwen.(2024).An Interpretable Image Denoising Framework via Dual Disentangled Representation Learning.IEEE TRANSACTIONS ON INTELLIGENT VEHICLES,9(1),2016-2030. |
MLA | Liang, Yunji,et al."An Interpretable Image Denoising Framework via Dual Disentangled Representation Learning".IEEE TRANSACTIONS ON INTELLIGENT VEHICLES 9.1(2024):2016-2030. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论