Seg-CycleGAN : SAR-to-optical image translation guided by a downstream task

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zhang, Hannuo, Li, Huihui, Lin, Jiarui, Zhang, Yujie, Fan, Jianghua, Liu, Hang
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914909429694464
author Zhang, Hannuo
Li, Huihui
Lin, Jiarui
Zhang, Yujie
Fan, Jianghua
Liu, Hang
author_facet Zhang, Hannuo
Li, Huihui
Lin, Jiarui
Zhang, Yujie
Fan, Jianghua
Liu, Hang
contents Optical remote sensing and Synthetic Aperture Radar(SAR) remote sensing are crucial for earth observation, offering complementary capabilities. While optical sensors provide high-quality images, they are limited by weather and lighting conditions. In contrast, SAR sensors can operate effectively under adverse conditions. This letter proposes a GAN-based SAR-to-optical image translation method named Seg-CycleGAN, designed to enhance the accuracy of ship target translation by leveraging semantic information from a pre-trained semantic segmentation model. Our method utilizes the downstream task of ship target semantic segmentation to guide the training of image translation network, improving the quality of output Optical-styled images. The potential of foundation-model-annotated datasets in SAR-to-optical translation tasks is revealed. This work suggests broader research and applications for downstream-task-guided frameworks. The code will be available at https://github.com/NPULHH/
format Preprint
id arxiv_https___arxiv_org_abs_2408_05777
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Seg-CycleGAN : SAR-to-optical image translation guided by a downstream task
Zhang, Hannuo
Li, Huihui
Lin, Jiarui
Zhang, Yujie
Fan, Jianghua
Liu, Hang
Computer Vision and Pattern Recognition
Artificial Intelligence
Image and Video Processing
Optical remote sensing and Synthetic Aperture Radar(SAR) remote sensing are crucial for earth observation, offering complementary capabilities. While optical sensors provide high-quality images, they are limited by weather and lighting conditions. In contrast, SAR sensors can operate effectively under adverse conditions. This letter proposes a GAN-based SAR-to-optical image translation method named Seg-CycleGAN, designed to enhance the accuracy of ship target translation by leveraging semantic information from a pre-trained semantic segmentation model. Our method utilizes the downstream task of ship target semantic segmentation to guide the training of image translation network, improving the quality of output Optical-styled images. The potential of foundation-model-annotated datasets in SAR-to-optical translation tasks is revealed. This work suggests broader research and applications for downstream-task-guided frameworks. The code will be available at https://github.com/NPULHH/
title Seg-CycleGAN : SAR-to-optical image translation guided by a downstream task
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Image and Video Processing
url https://arxiv.org/abs/2408.05777