Multi-Modality Image Super-Resolution using Generative Adversarial Networks
This addresses a domain-specific problem for computer vision applications like surveillance or autonomous driving, but appears incremental as it combines existing GAN-based techniques.
The paper tackles the joint problem of image super-resolution and multi-modality image-to-image translation, specifically recovering high-resolution day images from low-resolution night images, and presents two models with promising qualitative and quantitative results.
Over the past few years deep learning-based techniques such as Generative Adversarial Networks (GANs) have significantly improved solutions to image super-resolution and image-to-image translation problems. In this paper, we propose a solution to the joint problem of image super-resolution and multi-modality image-to-image translation. The problem can be stated as the recovery of a high-resolution image in a modality, given a low-resolution observation of the same image in an alternative modality. Our paper offers two models to address this problem and will be evaluated on the recovery of high-resolution day images given low-resolution night images of the same scene. Promising qualitative and quantitative results will be presented for each model.