Multi-task SAR Image Processing via GAN-based Unsupervised Manipulation

TL;DR

This paper introduces GUE, a GAN-based unsupervised framework for multi-task SAR image processing, capable of disentangling semantic features and performing various editing tasks without labeled data.

Contribution

It proposes a novel method to disentangle semantic directions in GAN latent space and enables multiple SAR image processing functions in a single unsupervised training.

Findings

Effective disentanglement of semantic directions in GAN latent space.

Successful multi-task SAR image processing including despeckling and rotation editing.

Validated through extensive experiments demonstrating robustness and versatility.

Abstract

Generative Adversarial Networks (GANs) have shown tremendous potential in synthesizing a large number of realistic SAR images by learning patterns in the data distribution. Some GANs can achieve image editing by introducing latent codes, demonstrating significant promise in SAR image processing. Compared to traditional SAR image processing methods, editing based on GAN latent space control is entirely unsupervised, allowing image processing to be conducted without any labeled data. Additionally, the information extracted from the data is more interpretable. This paper proposes a novel SAR image processing framework called GAN-based Unsupervised Editing (GUE), aiming to address the following two issues: (1) disentangling semantic directions in the GAN latent space and finding meaningful directions; (2) establishing a comprehensive SAR image processing framework while achieving multiple image processing functions. In the implementation of GUE, we decompose the entangled semantic directions in the GAN latent space by training a carefully designed network. Moreover, we can accomplish multiple SAR image processing tasks (including despeckling, localization, auxiliary identification, and rotation editing) in a single training process without any form of supervision. Extensive experiments validate the effectiveness of the proposed method.