GAN generation of synthetic multispectral satellite images

Abady, Lydia; Barni, Mauro; Garzelli, Andrea; Tondi, Benedetta

doi:10.1117/12.2575765

Cited by 38 publications

(31 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our experiments mainly involved two tasks: underwater image synthesis and underwater depth map estimation. For the first task, we synthesized underwater images from hazy in-air RGB-D images and evaluated the image qualities with multiple image generation models, including WaterGAN [ 16 ], CycleGAN [ 12 ], StarGAN [ 15 ], UW-Net [ 11 ], and NICE-GAN [ 32 ]. For the second task, we evaluated our depth map estimation results with a real underwater RGB-D dataset.…”

Section: Resultsmentioning

confidence: 99%

“…In addition, the results retain many artifacts, such as the desk in the last row of Figure 2 d. To retain the depth information for better underwater depth map estimation, UW-Net [ 11 ] takes the hazy in-air RGB-D images as input and uses DenseNet [ 24 ] for the generators, as shown in Figure 2 e; this method shows a fuzzy structure. The results of NICE-GAN [ 32 ] can be seen in Figure 2 f, and there are many artifacts in the results. Furthermore, most of the methods, including WaterGAN [ 16 ], CycleGAN [ 12 ], UW-Net [ 11 ], and NICE-GAN [ 32 ], are in two domains, and only StarGAN [ 15 ] can synthesize multi-style images.…”

Section: Resultsmentioning

confidence: 99%

“…The results of NICE-GAN [ 32 ] can be seen in Figure 2 f, and there are many artifacts in the results. Furthermore, most of the methods, including WaterGAN [ 16 ], CycleGAN [ 12 ], UW-Net [ 11 ], and NICE-GAN [ 32 ], are in two domains, and only StarGAN [ 15 ] can synthesize multi-style images. None of the above-mentioned methods consider the diversities in a given style.…”

Section: Resultsmentioning

confidence: 99%

“… Comparison of the visual quality of the synthetic underwater images using the following methods: WaterGAN [ 16 ], CycleGAN [ 12 ], StarGAN [ 15 ], UW-Net [ 11 ], NICE-GAN [ 32 ], and our method. …”

Section: Figurementioning

confidence: 99%

See 3 more Smart Citations

Unpaired Underwater Image Synthesis with a Disentangled Representation for Underwater Depth Map Prediction

Zhao

Zhou

et al. 2021

Sensors

View full text Add to dashboard Cite

As one of the key requirements for underwater exploration, underwater depth map estimation is of great importance in underwater vision research. Although significant progress has been achieved in the fields of image-to-image translation and depth map estimation, a gap between normal depth map estimation and underwater depth map estimation still remains. Additionally, it is a great challenge to build a mapping function that converts a single underwater image into an underwater depth map due to the lack of paired data. Moreover, the ever-changing underwater environment further intensifies the difficulty of finding an optimal mapping solution. To eliminate these bottlenecks, we developed a novel image-to-image framework for underwater image synthesis and depth map estimation in underwater conditions. For the problem of the lack of paired data, by translating hazy in-air images (with a depth map) into underwater images, we initially obtained a paired dataset of underwater images and corresponding depth maps. To enrich our synthesized underwater dataset, we further translated hazy in-air images into a series of continuously changing underwater images with a specified style. For the depth map estimation, we included a coarse-to-fine network to provide a precise depth map estimation result. We evaluated the efficiency of our framework for a real underwater RGB-D dataset. The experimental results show that our method can provide a diversity of underwater images and the best depth map estimation precision.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Figurementioning

confidence: 99%

See 2 more Smart Citations

Unpaired Underwater Image Synthesis with a Disentangled Representation for Underwater Depth Map Prediction

Zhao

Zhou

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…In [ 13 ], they generated synthetic spectral bands for archive satellite images using Landsat data. Synthetic satellite imagery generation from Sentinel-2 (with the spatial resolution more than 10 meters per pixel) was considered in [ 14 , 15 ]. However, in our work, we were focused on high-resolution satellite images as they provide valuable texture information.…”

Section: Introductionmentioning

confidence: 99%

Generation of the NIR Spectral Band for Satellite Images with Convolutional Neural Networks

Illarionova

Shadrin

Trekin

et al. 2021

Sensors

View full text Add to dashboard Cite

The near-infrared (NIR) spectral range (from 780 to 2500 nm) of the multispectral remote sensing imagery provides vital information for landcover classification, especially concerning vegetation assessment. Despite the usefulness of NIR, it does not always accomplish common RGB. Modern achievements in image processing via deep neural networks make it possible to generate artificial spectral information, for example, to solve the image colorization problem. In this research, we aim to investigate whether this approach can produce not only visually similar images but also an artificial spectral band that can improve the performance of computer vision algorithms for solving remote sensing tasks. We study the use of a generative adversarial network (GAN) approach in the task of the NIR band generation using only RGB channels of high-resolution satellite imagery. We evaluate the impact of a generated channel on the model performance to solve the forest segmentation task. Our results show an increase in model accuracy when using generated NIR compared to the baseline model, which uses only RGB (0.947 and 0.914 F1-scores, respectively). The presented study shows the advantages of generating the extra band such as the opportunity to reduce the required amount of labeled data.

show abstract

Remote Sensing and Modeling Soil Organic Carbon Sequestration: A Regime in Global Climate Change

Dey,

Sharma

2024

Sustainable Plant Nutrition in a Changing World

View full text Add to dashboard Cite

GAN generation of synthetic multispectral satellite images

Cited by 38 publications

References 6 publications

Unpaired Underwater Image Synthesis with a Disentangled Representation for Underwater Depth Map Prediction

Unpaired Underwater Image Synthesis with a Disentangled Representation for Underwater Depth Map Prediction

Generation of the NIR Spectral Band for Satellite Images with Convolutional Neural Networks

Remote Sensing and Modeling Soil Organic Carbon Sequestration: A Regime in Global Climate Change

Contact Info

Product

Resources

About