StawGAN: Structural-Aware Generative Adversarial Networks for Infrared Image Translation
This work addresses a domain-specific problem for applications like aerial surveillance using drones, but it is incremental as it builds on existing image translation methods.
The paper tackles the problem of translating night-time thermal infrared images to daytime color images to improve object perception, introducing StawGAN which produces more accurate translations with better-shaped and high-definition objects compared to other state-of-the-art models.
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