StawGAN: Structural-Aware Generative Adversarial Networks for Infrared Image Translation

Luigi Sigillo, Eleonora Grassucci, Danilo Comminiello
5/18/2023
cs.CVcs.LGeess.IV

Official code: LuigiSigillo/StawGAN (19 stars, last commit 2023-10-18).

Abstract

This paper addresses the problem of translating night-time thermal infrared images, which are the most adopted image modalities to analyze night-time scenes, to daytime color images (NTIT2DC), which provide better perceptions of objects. We introduce a novel model that focuses on enhancing the quality of the target generation without merely colorizing it. The proposed structural aware (StawGAN) enables the translation of better-shaped and high-definition objects in the target domain. We test our model on aerial images of the DroneVeichle dataset containing RGB-IR paired images. The proposed approach produces a more accurate translation with respect to other state-of-the-art image translation models. The source code is available at https://github.com/LuigiSigillo/StawGAN

View on arXivView PDF

Code Implementations(1)

LuigiSigillo/StawGANOfficial100%

Official PyTorch repository for StawGAN: Structural-Aware Generative Adversarial Networks for Infrared Image Translation

191PythonSep 20, 20223 years ago

Similar Papers

Nighttime Thermal Infrared Image Colorization with Feedback-based Object Appearance Learning

85% match1 repo22023

LadleNet: A Two-Stage UNet for Infrared Image to Visible Image Translation Guided by Semantic Segmentation

83% match2023

Visible to Thermal image Translation for improving visual task in low light conditions

82% match2023

RGB-to-IR image translation for infrared vehicle detection in unseen UAV domains

82% match2026

MTSIC: Multi-stage Transformer-based GAN for Spectral Infrared Image Colorization

81% match2025

F-ViTA: Foundation Model Guided Visible to Thermal Translation

81% match1 repo432025

Cite this paper

@article{sigillo2023stawgan,
  title  = {StawGAN: Structural-Aware Generative Adversarial Networks for Infrared Image Translation},
  author = {Luigi Sigillo and Eleonora Grassucci and Danilo Comminiello},
  year   = {2023},
  eprint = {2305.10882},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2305.10882v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2305.10882.svg)](https://codeofpaper.com/paper/2305.10882)

Discussion