A study of enhanced visual perception of marine biology images based on diffusion-GAN
Abstract Aiming at the influence of factors such as the special optical characteristics of water bodies on the perceptual quality of generated images, this paper proposes the DifSG2-CCL model for reducing the special optical characteristics of water bodies and the DPL-SG2 model for introducing perce...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer
2025-03-01
|
| Series: | Complex & Intelligent Systems |
| Subjects: | |
| Online Access: | https://doi.org/10.1007/s40747-025-01832-w |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850042276093362176 |
|---|---|
| author | Feifan Yao Huiying Zhang Yifei Gong Qinghua Zhang Pan Xiao |
| author_facet | Feifan Yao Huiying Zhang Yifei Gong Qinghua Zhang Pan Xiao |
| author_sort | Feifan Yao |
| collection | DOAJ |
| description | Abstract Aiming at the influence of factors such as the special optical characteristics of water bodies on the perceptual quality of generated images, this paper proposes the DifSG2-CCL model for reducing the special optical characteristics of water bodies and the DPL-SG2 model for introducing perceptual loss. Combining the ideas of cyclic consistency and style migration, this paper builds the Underwater Cycle Consistency Loss (U-CCL) module. The DifSG2-CCL model is based on the method of image reconstruction, which converts the underwater image into the style of the land image to reduce the influence of the water body factors. VGG16 is introduced as a perceptual loss into the DPL-SG2 to enhance the visual perception of the image by feature extraction with different layers and tonal weighting. Furthermore, in addition to the already disclosed SA dataset, a T dataset with a resolution of 256 × 256 in 9.366k sheets is provided in this paper. The experimental results show that DifSG2-CCL and DPL-SG2 can effectively enhance the perceptual quality of the images. The unique underwater image generation of DifSG2-CCL produces excellent results in qualitative analysis and reduces its FID value to 8.97. DPL-SG2 is more outstanding in the training of T dataset, and its FID value is reduced to 5.39. Therefore, the U-CCL and VGG16 can be applied as an innovative approach to enhance visual perception of underwater images. The experimental code with pre-trained models will be published shortly at https://github.com/yff0428/DPL-SG2/tree/main . |
| format | Article |
| id | doaj-art-d879761f78224eb8b33f8a909964c8f3 |
| institution | DOAJ |
| issn | 2199-4536 2198-6053 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | Springer |
| record_format | Article |
| series | Complex & Intelligent Systems |
| spelling | doaj-art-d879761f78224eb8b33f8a909964c8f32025-08-20T02:55:36ZengSpringerComplex & Intelligent Systems2199-45362198-60532025-03-0111512010.1007/s40747-025-01832-wA study of enhanced visual perception of marine biology images based on diffusion-GANFeifan Yao0Huiying Zhang1Yifei Gong2Qinghua Zhang3Pan Xiao4Jilin Institute of Chemical TechnologyJilin Institute of Chemical TechnologyJilin Institute of Chemical TechnologyJilin Institute of Chemical TechnologyJilin Institute of Chemical TechnologyAbstract Aiming at the influence of factors such as the special optical characteristics of water bodies on the perceptual quality of generated images, this paper proposes the DifSG2-CCL model for reducing the special optical characteristics of water bodies and the DPL-SG2 model for introducing perceptual loss. Combining the ideas of cyclic consistency and style migration, this paper builds the Underwater Cycle Consistency Loss (U-CCL) module. The DifSG2-CCL model is based on the method of image reconstruction, which converts the underwater image into the style of the land image to reduce the influence of the water body factors. VGG16 is introduced as a perceptual loss into the DPL-SG2 to enhance the visual perception of the image by feature extraction with different layers and tonal weighting. Furthermore, in addition to the already disclosed SA dataset, a T dataset with a resolution of 256 × 256 in 9.366k sheets is provided in this paper. The experimental results show that DifSG2-CCL and DPL-SG2 can effectively enhance the perceptual quality of the images. The unique underwater image generation of DifSG2-CCL produces excellent results in qualitative analysis and reduces its FID value to 8.97. DPL-SG2 is more outstanding in the training of T dataset, and its FID value is reduced to 5.39. Therefore, the U-CCL and VGG16 can be applied as an innovative approach to enhance visual perception of underwater images. The experimental code with pre-trained models will be published shortly at https://github.com/yff0428/DPL-SG2/tree/main .https://doi.org/10.1007/s40747-025-01832-wVisual perceptionDifSG2-CCLDPL-SG2SA datasetT dataset |
| spellingShingle | Feifan Yao Huiying Zhang Yifei Gong Qinghua Zhang Pan Xiao A study of enhanced visual perception of marine biology images based on diffusion-GAN Complex & Intelligent Systems Visual perception DifSG2-CCL DPL-SG2 SA dataset T dataset |
| title | A study of enhanced visual perception of marine biology images based on diffusion-GAN |
| title_full | A study of enhanced visual perception of marine biology images based on diffusion-GAN |
| title_fullStr | A study of enhanced visual perception of marine biology images based on diffusion-GAN |
| title_full_unstemmed | A study of enhanced visual perception of marine biology images based on diffusion-GAN |
| title_short | A study of enhanced visual perception of marine biology images based on diffusion-GAN |
| title_sort | study of enhanced visual perception of marine biology images based on diffusion gan |
| topic | Visual perception DifSG2-CCL DPL-SG2 SA dataset T dataset |
| url | https://doi.org/10.1007/s40747-025-01832-w |
| work_keys_str_mv | AT feifanyao astudyofenhancedvisualperceptionofmarinebiologyimagesbasedondiffusiongan AT huiyingzhang astudyofenhancedvisualperceptionofmarinebiologyimagesbasedondiffusiongan AT yifeigong astudyofenhancedvisualperceptionofmarinebiologyimagesbasedondiffusiongan AT qinghuazhang astudyofenhancedvisualperceptionofmarinebiologyimagesbasedondiffusiongan AT panxiao astudyofenhancedvisualperceptionofmarinebiologyimagesbasedondiffusiongan AT feifanyao studyofenhancedvisualperceptionofmarinebiologyimagesbasedondiffusiongan AT huiyingzhang studyofenhancedvisualperceptionofmarinebiologyimagesbasedondiffusiongan AT yifeigong studyofenhancedvisualperceptionofmarinebiologyimagesbasedondiffusiongan AT qinghuazhang studyofenhancedvisualperceptionofmarinebiologyimagesbasedondiffusiongan AT panxiao studyofenhancedvisualperceptionofmarinebiologyimagesbasedondiffusiongan |