# Learning a Dilated Residual Network for SAR Image Despeckling

arXiv: https://arxiv.org/abs/1709.02898 · HTML: https://mlsanity.com/paper/1709.02898/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Sep 2017.

## Built on by (most cited first, 9 of 9)

- [As if by magic: self-supervised training of deep despeckling networks with MERLIN](https://mlsanity.com/paper/2110.13148/) (2021)
- [Exploiting multi-temporal information for improved speckle reduction of Sentinel-1 SAR images by deep learning](https://mlsanity.com/paper/2102.00682/) (2021)
- [A Tunable Despeckling Neural Network Stabilized via Diffusion Equation](https://mlsanity.com/paper/2411.15921/) (2024)
- [NeighCNN: A CNN based SAR Speckle Reduction using Feature preserving Loss Function](https://mlsanity.com/paper/2108.11573/) (2021)
- [Deep Learning Based Speckle Filtering for Polarimetric SAR Images. Application to Sentinel-1](https://mlsanity.com/paper/2408.15678/) (2024)
- [Monte Carlo Maximum Likelihood Reconstruction for Digital Holography with Speckle](https://mlsanity.com/paper/2602.10344/) (2026)
- [PowerFusion: A Tensor Compiler with Explicit Data Movement Description and Instruction-level Graph IR](https://mlsanity.com/paper/2307.04995/) (2023)
- [Multi-task SAR Image Processing via GAN-based Unsupervised Manipulation](https://mlsanity.com/paper/2408.01553/) (2024)
- [SAR-FAH: A Frequency-Adaptive Hybrid Network based on Neural ODEs for Structural-Preserving SAR Despeckling](https://mlsanity.com/paper/2511.05890/) (2025)

## Abstract (arXiv)

In this paper, to break the limit of the traditional linear models for synthetic aperture radar (SAR) image despeckling, we propose 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). SAR-DRN is based on dilated convolutions, which can both enlarge the receptive field and maintain the filter size and layer depth with a lightweight structure. In addition, skip connections and residual learning strategy are added to the despeckling model to maintain the image details and reduce the vanishing gradient problem. Compared with the traditional despeckling methods, the proposed method shows superior performance over the state-of-the-art methods on both quantitative and visual assessments, especially for strong speckle noise.