Hyperspectral Image Denoising via Adversarial Learning
Due to sensor instability and atmospheric interference, hyperspectral images (HSIs) often suffer from different kinds of noise which degrade the performance of downstream tasks. Therefore, HSI denoising has become an essential part of HSI preprocessing. Traditional methods tend to tackle one specifi...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-04-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/8/1790 |
| _version_ | 1827619507094421504 |
|---|---|
| author | Junjie Zhang Zhouyin Cai Fansheng Chen Dan Zeng |
| author_facet | Junjie Zhang Zhouyin Cai Fansheng Chen Dan Zeng |
| author_sort | Junjie Zhang |
| collection | DOAJ |
| description | Due to sensor instability and atmospheric interference, hyperspectral images (HSIs) often suffer from different kinds of noise which degrade the performance of downstream tasks. Therefore, HSI denoising has become an essential part of HSI preprocessing. Traditional methods tend to tackle one specific type of noise and remove it iteratively, resulting in drawbacks including inefficiency when dealing with mixed noise. Most recently, deep neural network-based models, especially generative adversarial networks, have demonstrated promising performance in generic image denoising. However, in contrast to generic RGB images, HSIs often possess abundant spectral information; thus, it is non-trivial to design a denoising network to effectively explore both spatial and spectral characteristics simultaneously. To address the above issues, in this paper, we propose an end-to-end HSI denoising model via adversarial learning. More specifically, to capture the subtle noise distribution from both spatial and spectral dimensions, we designed a Residual Spatial-Spectral Module (RSSM) and embed it in an UNet-like structure as the generator to obtain clean images. To distinguish the real image from the generated one, we designed a discriminator based on the Multiscale Feature Fusion Module (MFFM) to further improve the quality of the denoising results. The generator was trained with joint loss functions, including reconstruction loss, structural loss and adversarial loss. Moreover, considering the lack of publicly available training data for the HSI denoising task, we collected an additional benchmark dataset denoted as the Shandong Feicheng Denoising (SFD) dataset. We evaluated five types of mixed noise across several datasets in comparative experiments, and comprehensive experimental results on both simulated and real data demonstrate that the proposed model achieves competitive results against state-of-the-art methods. For ablation studies, we investigated the structure of the generator as well as the training process with joint losses and different amounts of training data, further validating the rationality and effectiveness of the proposed method. |
| first_indexed | 2024-03-09T10:30:06Z |
| format | Article |
| id | doaj.art-60fa9137871d47009923f296a9c11f9c |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T10:30:06Z |
| publishDate | 2022-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-60fa9137871d47009923f296a9c11f9c2023-12-01T21:21:51ZengMDPI AGRemote Sensing2072-42922022-04-01148179010.3390/rs14081790Hyperspectral Image Denoising via Adversarial LearningJunjie Zhang0Zhouyin Cai1Fansheng Chen2Dan Zeng3Key Laboratory of Specialty Fiber Optics and Optical Access Networks, Joint International Research Laboratory of Specialty Fiber Optics and Advanced Communication, Shanghai Institute of Advanced Communication and Data Science, Shanghai University, Shanghai 200444, ChinaKey Laboratory of Specialty Fiber Optics and Optical Access Networks, Joint International Research Laboratory of Specialty Fiber Optics and Advanced Communication, Shanghai Institute of Advanced Communication and Data Science, Shanghai University, Shanghai 200444, ChinaHangzhou Institute for Advanced Study, University of Chinese Academy of Sciences, Hangzhou 310024, ChinaKey Laboratory of Specialty Fiber Optics and Optical Access Networks, Joint International Research Laboratory of Specialty Fiber Optics and Advanced Communication, Shanghai Institute of Advanced Communication and Data Science, Shanghai University, Shanghai 200444, ChinaDue to sensor instability and atmospheric interference, hyperspectral images (HSIs) often suffer from different kinds of noise which degrade the performance of downstream tasks. Therefore, HSI denoising has become an essential part of HSI preprocessing. Traditional methods tend to tackle one specific type of noise and remove it iteratively, resulting in drawbacks including inefficiency when dealing with mixed noise. Most recently, deep neural network-based models, especially generative adversarial networks, have demonstrated promising performance in generic image denoising. However, in contrast to generic RGB images, HSIs often possess abundant spectral information; thus, it is non-trivial to design a denoising network to effectively explore both spatial and spectral characteristics simultaneously. To address the above issues, in this paper, we propose an end-to-end HSI denoising model via adversarial learning. More specifically, to capture the subtle noise distribution from both spatial and spectral dimensions, we designed a Residual Spatial-Spectral Module (RSSM) and embed it in an UNet-like structure as the generator to obtain clean images. To distinguish the real image from the generated one, we designed a discriminator based on the Multiscale Feature Fusion Module (MFFM) to further improve the quality of the denoising results. The generator was trained with joint loss functions, including reconstruction loss, structural loss and adversarial loss. Moreover, considering the lack of publicly available training data for the HSI denoising task, we collected an additional benchmark dataset denoted as the Shandong Feicheng Denoising (SFD) dataset. We evaluated five types of mixed noise across several datasets in comparative experiments, and comprehensive experimental results on both simulated and real data demonstrate that the proposed model achieves competitive results against state-of-the-art methods. For ablation studies, we investigated the structure of the generator as well as the training process with joint losses and different amounts of training data, further validating the rationality and effectiveness of the proposed method.https://www.mdpi.com/2072-4292/14/8/1790hyperspectral imagesimage denoisingadversarial learning mechanismresidual learning |
| spellingShingle | Junjie Zhang Zhouyin Cai Fansheng Chen Dan Zeng Hyperspectral Image Denoising via Adversarial Learning Remote Sensing hyperspectral images image denoising adversarial learning mechanism residual learning |
| title | Hyperspectral Image Denoising via Adversarial Learning |
| title_full | Hyperspectral Image Denoising via Adversarial Learning |
| title_fullStr | Hyperspectral Image Denoising via Adversarial Learning |
| title_full_unstemmed | Hyperspectral Image Denoising via Adversarial Learning |
| title_short | Hyperspectral Image Denoising via Adversarial Learning |
| title_sort | hyperspectral image denoising via adversarial learning |
| topic | hyperspectral images image denoising adversarial learning mechanism residual learning |
| url | https://www.mdpi.com/2072-4292/14/8/1790 |
| work_keys_str_mv | AT junjiezhang hyperspectralimagedenoisingviaadversariallearning AT zhouyincai hyperspectralimagedenoisingviaadversariallearning AT fanshengchen hyperspectralimagedenoisingviaadversariallearning AT danzeng hyperspectralimagedenoisingviaadversariallearning |