Encoder-Free Multiaxis Physics-Aware Fusion Network for Remote Sensing Image Dehazing

Wen, Yuanbo; Gao, Tao; Zhang, Jing; Li, Ziqi; Chen, Ting

doi:10.1109/tgrs.2023.3325927

Cited by 9 publications

(2 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The same as SateHaze1k, the resolution of the images in RICE is

. RRSD300 [ 42 ]: To further demonstrate the universality of the proposed method, we conducted experiments on the real-world dataset RRSD300. RRSD300 is a dataset containing 300 real remote sensing haze images and not containing paired clear images.…”

Section: Resultsmentioning

confidence: 99%

Frequency-Oriented Transformer for Remote Sensing Image Dehazing

Zhang,

He,

Zhan

et al. 2024

Sensors

View full text Add to dashboard Cite

Remote sensing images are inevitably affected by the degradation of haze with complex appearance and non-uniform distribution, which remarkably affects the effectiveness of downstream remote sensing visual tasks. However, most current methods principally operate in the original pixel space of the image, which hinders the exploration of the frequency characteristics of remote sensing images, resulting in these models failing to fully exploit their representation ability to produce high-quality images. This paper proposes a frequency-oriented remote sensing dehazing Transformer named FOTformer, to explore information in the frequency domain to eliminate disturbances caused by haze in remote sensing images. It contains three components. Specifically, we developed a frequency-prompt attention evaluator to estimate the self-correlation of features in the frequency domain rather than the spatial domain, improving the image restoration performance. We propose a content reconstruction feed-forward network that captures information between different scales in features and integrates and processes global frequency domain information and local multi-scale spatial information in Fourier space to reconstruct the global content under the guidance of the amplitude spectrum. We designed a spatial-frequency aggregation block to exchange and fuse features from the frequency domain and spatial domain of the encoder and decoder to facilitate the propagation of features from the encoder stream to the decoder and alleviate the problem of information loss in the network. The experimental results show that the FOTformer achieved a more competitive performance against other remote sensing dehazing methods on commonly used benchmark datasets.

show abstract

“…The same as SateHaze1k, the resolution of the images in RICE is

Section: Resultsmentioning

confidence: 99%

Frequency-Oriented Transformer for Remote Sensing Image Dehazing

Zhang,

He,

Zhan

et al. 2024

Sensors

View full text Add to dashboard Cite

show abstract

“…Images taken during rainy weather condition frequently exhibit reduced visibility caused by rain streaks [3,35,36,43]. This degradation severely impedes multiple computer vision tasks [10,34,42], including detection, segmentation, and video surveillance. There are significant interests in developing methods to mitigate the rain degradation and reconstruct the photo-realistic details.…”

Section: Introductionmentioning

confidence: 99%

iVoiding: A Thermal-Image based Artificial Intelligence Dynamic Voiding Detection System

Chen

Tsai

et al. 2022

2022 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)

View full text Add to dashboard Cite

Existing unpaired image deraining approaches face challenges in accurately capture the distinguishing characteristics between the rainy and clean domains, resulting in residual degradation and color distortion within the reconstructed images. To this end, we propose an energy-informed diffusion model for unpaired photorealistic image deraining (UPID-EDM). Initially, we delve into the intricate visual-language priors embedded within the contrastive language-image pre-training model (CLIP), and demonstrate that the CLIP priors aid in the discrimination of rainy and clean images. Furthermore, we introduce a dual-consistent energy function (DEF) that retains the rain-irrelevant characteristics while eliminating the rain-relevant features. This energy function is trained by the non-corresponding rainy and clean images. In addition, we employ the rain-relevance discarding energy function (RDEF) and the rainirrelevance preserving energy function (RPEF) to direct the reverse sampling procedure of a pre-trained diffusion model, effectively removing the rain streaks while preserving the image contents. Extensive experiments demonstrate that our energy-informed model surpasses the existing unpaired learning approaches in terms of both supervised and no-reference metrics.

show abstract