Domain Adaptation for Underwater Image Enhancement

Wang, Zhengyong; Shen, Liquan; Yu, Mei; Wang, Kun; Lin, Yufei; Xu, Mai

doi:10.1109/tip.2023.3244647

Cited by 29 publications

(9 citation statements)

References 72 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…underwater, adverse illumination or weather conditions. To restore degraded input image, most of previous works design task specific model for each adverse environment such as underwater [9,39], low-light [37], rainy day [2,22,26,31,32,42,48], haze [1,10,14,18,20,41,44], and snow [6,7,28,50]. However, to deploy multiple model for different scenario is resource in-efficiency for practical usage.…”

Section: Heavy Snow Light Snowmentioning

confidence: 99%

“…Inspired by inter&intra-domain adaptation literature for image enhancement [39], we view the problem from data domain perspective and observed that multi-domain obstacles are not only existed between different weather types, the diverse weather severity also introduce multi-domain in intra-domain of weather type, which is ignored by most of previous works, and further limit their performance. As shown in Fig.…”

Section: Heavy Snow Light Snowmentioning

confidence: 99%

“…As severity, we develop based on the intuitively observation that the more severely degraded image produce worse Image Quality Assessment (IQA) score, and IQA score is positively related to restoration level that require to apply to restore clean image. Motivated by previous works [39,51] that demonstrate the effectiveness of learning a image quality ranker with Marginal Ranking Loss (MRL) to benefit the following image restoration, we train a ranker to predict weather severity information. Nevertheless, the standard MRL only consider the ranking information between input image pairs, that make the ranker prone to predict incorrect IQA score interval, and leading to apply inappropriate restoration level while use the predicted IQA score as restoration level signal.…”

Section: Heavy Snow Light Snowmentioning

confidence: 99%

“…Severity Aware Image Restoration Apart from degradation type, degradation severity also bring various appearance and difficulty to restore, many prior works [2,6,11,21,39,48] have been demonstrated the effectiveness of taking degradation severity into account for image restoration. DID-MDN [48] proposed a rain density aware model and divide rain level to light, medium and heavy rain for better restore images, a similar work also done by [2].…”

Section: Related Workmentioning

confidence: 99%

See 3 more Smart Citations

A study of adults' orientations to learning at the national open university of Taiwan

Chen¹

View full text Add to dashboard Cite

Lifelogging has gained more attention due to its wide applications, such as personalized recommendations or memory assistance. The issues of collecting and extracting personal life events have emerged. People often share their life experiences with others through conversations. However, extracting life events from conversations is rarely explored. In this paper, we present Life Event Dialog, a dataset containing fine-grained life event annotations on conversational data. In addition, we initiate a novel conversational life event extraction task and differentiate the task from the public event extraction or the life event extraction from other sources like microblogs. We explore three information extraction (IE) frameworks to address the conversational life event extraction task: OpenIE, relation extraction, and event extraction. A comprehensive empirical analysis of the three baselines is established. The results suggest that the current event extraction model still struggles with extracting life events from human daily conversations. Our proposed life event dialog dataset and in-depth analysis of IE frameworks will facilitate future research on life event extraction from conversations.

show abstract

Section: Heavy Snow Light Snowmentioning

confidence: 99%

Section: Heavy Snow Light Snowmentioning

confidence: 99%

Section: Heavy Snow Light Snowmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

A study of adults' orientations to learning at the national open university of Taiwan

Chen¹

View full text Add to dashboard Cite

show abstract

“…highlighted (Wang et al, 2023), although enhancing these poorquality underwater images has been a challenging prerequisite for underwater object detection, monocular depth estimation, and underwater object tracking (Gao et al, 2019).…”

mentioning

confidence: 99%

An underwater image enhancement model for domain adaptation

Deng

Liu

et al. 2023

Front. Mar. Sci.

View full text Add to dashboard Cite

Underwater imaging has been suffering from color imbalance, low contrast, and low-light environment due to strong spectral attenuation of light in the water. Owing to its complex physical imaging mechanism, enhancing the underwater imaging quality based on the deep learning method has been well-developed recently. However, individual studies use different underwater image datasets, leading to low generalization ability in other water conditions. To solve this domain adaptation problem, this paper proposes an underwater image enhancement scheme that combines individually degraded images and publicly available datasets for domain adaptation. Firstly, an underwater dataset fitting model (UDFM) is proposed to merge the individual localized and publicly available degraded datasets into a combined degraded one. Then an underwater image enhancement model (UIEM) is developed base on the combined degraded and open available clear image pairs dataset. The experiment proves that clear images can be recovered by only collecting the degraded images at some specific sea area. Thus, by use of the scheme in this study, the domain adaptation problem could be solved with the increase of underwater images collected at various sea areas. Also, the generalization ability of the underwater image enhancement model is supposed to become more robust. The code is available at https://github.com/fanren5599/UIEM.

show abstract

UP‐GAN: Channel‐spatial attention‐based progressive generative adversarial network for underwater image enhancement

Wang,

Chen,

Wei

et al. 2024

Journal of Field Robotics

View full text Add to dashboard Cite

Focusing on severe color deviation, low brightness, and mixed noise caused by inherent scattering and light attenuation effects within underwater environments, an underwater‐attention progressive generative adversarial network (UP‐GAN) is innovated for underwater image enhancement (UIE). Salient contributions are as follows: (1) By elaborately devising an underwater background light estimation module via an underwater imaging model, the degradation mechanism can be sufficiently integrated to fuse prior information, which in turn saves computational burden on subsequent enhancement; (2) to suppress mixed noise and enhance foreground, simultaneously, an underwater dual‐attention module is created to fertilize skip connection from channel and spatial aspects, thereby getting rid of noise amplification within the UIE; and (3) by systematically combining with spatial consistency, exposure control, color constancy, color relative dispersion losses, the entire UP‐GAN framework is skillfully optimized by taking into account multidegradation factors. Comprehensive experiments conducted on the UIEB data set demonstrate the effectiveness and superiority of the proposed UP‐GAN in terms of both subjective and objective aspects.

show abstract

Domain Adaptation for Underwater Image Enhancement

Cited by 29 publications

References 72 publications

A study of adults' orientations to learning at the national open university of Taiwan

A study of adults' orientations to learning at the national open university of Taiwan

An underwater image enhancement model for domain adaptation

UP‐GAN: Channel‐spatial attention‐based progressive generative adversarial network for underwater image enhancement

Contact Info

Product

Resources

About