3260 papers • 126 benchmarks • 313 datasets
Despeckling is the task of suppressing speckle from Synthetic Aperture Radar (SAR) acquisitions. Image credits: GRD Sentinel-1 SAR image despeckled with SAR2SAR-GRD
(Image credit: Papersgraph)
These leaderboards are used to track progress in sar-image-despeckling-6
No benchmarks available.
Use these libraries to find sar-image-despeckling-6 models and implementations
No datasets available.
No subtasks available.
A deep learning algorithm with semi-supervision is proposed in this article: SAR2SAR, where Multitemporal time series are leveraged and the neural network learns to restore SAR images by only looking at noisy acquisitions.
A novel deep learning approach by learning a non-linear end-to-end mapping between the noisy and clean SAR images with a dilated residual network (SAR-DRN), which shows superior performance over the state-of-the-art methods on both quantitative and visual assessments.
A deep-learning-based approach called, image despeckling convolutional neural network (ID-CNN), for automatically removing speckle from the input noisy images, which achieves significant improvements over the state-of-the-art speckel reduction methods.
This paper analyzes different strategies one can adopt, depending on the speckle removal task one wishes to perform and the availability of multitemporal stacks of SAR data, and proposed methods are compared to other state-of-the-art speckled removal filters.
A self-supervised Bayesian despeckling method that can learn features of real SAR images rather than synthetic data and is superior on real data in both quantitative and visual assessments is proposed.
A self-supervised strategy based on the separation of the real and imaginary parts of single-look complex (SLC) SAR images, called coMplex sElf-supeRvised despeckLINg (MERLIN), is introduced and it is shown that it offers a straightforward way to train all kinds of deep despekling networks.
A new method is introduced for SAR image despeckling (SAR-CAM), which improves the performance of an encoder–decoder CNN architecture by using various attention modules and a context block is introduced at the minimum scale to capture multiscale information.
The proposed despeckling network comprises of a transformer-based encoder which allows the network to learn global dependencies between different image regions - aiding in better despekling.
Adding a benchmark result helps the community track progress.