Thermal Infrared Colorization via Conditional Generative Adversarial Network

2018/10/12 by Xiaodong Kuang, Kuang, Xiaodong, Xiubao Sui +9 · 3 citations
Computer Science · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #cs.CV

paper · pdf · doi:10.48550/arxiv.1810.05399

arxiv created 2018/11/05 · arxiv updated 2018/11/06

Abstract

Transforming a thermal infrared image into a realistic RGB image is a challenging task. In this paper we propose a deep learning method to bridge this gap. We propose learning the transformation mapping using a coarse-to-fine generator that preserves the details. Since the standard mean squared loss cannot penalize the distance between colorized and ground truth images well, we propose a composite loss function that combines content, adversarial, perceptual and total variation losses. The content loss is used to recover global image information while the latter three losses are used to synthesize local realistic textures. Quantitative and qualitative experiments demonstrate that our approach significantly outperforms existing approaches.

Cited by

• Contrast-Guided Cross-Modal Distillation for Thermal Object Detection
• A Kernel Space-based Multidimensional Sparse Model for Dynamic PET Image Denoising
• MTSIC: Multi-stage Transformer-based GAN for Spectral Infrared Image Colorization

Related

• Robust Perceptual Night Vision in Thermal Colorization
• Infrared Colorization Using Deep Convolutional Neural Networks
• MTSIC: Multi-stage Transformer-based GAN for Spectral Infrared Image Colorization
• DEAL: Data-Efficient Adversarial Learning for High-Quality Infrared Imaging
• Self-training Guided Adversarial Domain Adaptation For Thermal Imagery