Generative adversarial networks and perceptual losses for video super-resolution Lucas, Alice López Tapia, Santiago Molina Soriano, Rafael Katsaggelos, Aggelos K. Artificial neural networks video signal processing image resolution image generation Video super-resolution (VSR) has become one of the most critical problems in video processing. In the deep learning literature, recent works have shown the benefits of using adversarial-based and perceptual losses to improve the performance on various image restoration tasks; however, these have yet to be applied for video super-resolution. In this paper, we propose a generative adversarial network (GAN)-based formulation for VSR. We introduce a new generator network optimized for the VSR problem, named VSRResNet, along with new discriminator architecture to properly guide VSRResNet during the GAN training. We further enhance our VSR GAN formulation with two regularizers, a distance loss in feature-space and pixel-space, to obtain our final VSRResFeatGAN model. We show that pre-training our generator with the mean-squarederror loss only quantitatively surpasses the current state-of-theart VSR models. Finally, we employ the PercepDist metric to compare the state-of-the-art VSR models. We show that this metric more accurately evaluates the perceptual quality of SR solutions obtained from neural networks, compared with the commonly used PSNR/SSIM metrics. Finally, we show that our proposed model, the VSRResFeatGAN model, outperforms the current state-of-the-art SR models, both quantitatively and qualitatively 2025-01-15T07:24:26Z 2025-01-15T07:24:26Z 2019 journal article Lucas, A., López-Tapia, S., Molina, R., Katsaggelos, A.K., Generative Adversarial Networks and Perceptual Losses for Video Super-Resolution, IEEE Transactions on Image Processing, volumen 28, número 73312-3327 https://hdl.handle.net/10481/99160 10.1109/TIP.2019.2895768 eng http://creativecommons.org/licenses/by-nc-nd/4.0/ open access Attribution-NonCommercial-NoDerivatives 4.0 Internacional IEEE