中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 多模态人工智能系统全国重点实验室
  5. 互联网大数据与安全信息学研究中心
An Interpretable Image Denoising Framework via Dual Disentangled Representation Learning

文献类型：期刊论文

作者Liang, Yunji1; Fan, Jiayuan1; Zheng, Xiaolong2; Wang, Yutong3; Huangfu, Luwen4,5; Ghavate, Vedant6; Yu, Zhiwen1
刊名IEEE TRANSACTIONS ON INTELLIGENT VEHICLES
出版日期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
DOI10.1109/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.
WOS关键词WEATHER ; NETWORK ; SNOW ; RAIN
资助项目Natural Science Foundation of China[62372378] ; Natural Science Foundation of China[72225011]
WOS研究方向Computer Science ; Engineering ; Transportation
语种英语
WOS记录号WOS:001173317800171
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
资助机构Natural Science Foundation of China
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_互联网大数据与安全信息学研究中心
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.Northwestern Polytech Univ, Sch Comp Sci, Xian 710072, Peoples R China
2.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Sys, Beijing 100190, Peoples R China
3.Chinese Acad Sci, Inst Automat, State Key Lab Multimodal Artificial Intelligence, Beijing 100190, Peoples R China
4.San Diego State Univ, Fowler Coll Business FCB, San Diego, CA 92182 USA
5.San Diego State Univ SDSU, Ctr Human Dynam Mobile Age HDMA, San Diego, CA 92182 USA
6.San Diego State Univ SDSU, Coll Arts & Letters, San Diego, CA 92182 USA
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.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

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。