Recently, video super resolution (VSR) has become a very impactful task in the area of Computer Vision due to its various applications. In this paper, we propose Recurrent Back-Projection Generative Adversarial Network (RBPGAN) for VSR in an attempt to generate temporally coherent solutions while preserving spatial details. RBPGAN integrates two state-of-the-art models to get the best in both worlds without compromising the accuracy of produced video. The generator of the model is inspired by RBPN system, while the discriminator is inspired by TecoGAN. We also utilize Ping-Pong loss to increase temporal consistency over time. Our contribution together results in a model that outperforms earlier work in terms of temporally consistent details, as we will demonstrate qualitatively and quantitatively using different datasets.

翻译：近年来，视频超分辨率（VSR）因其广泛的应用而成为计算机视觉领域极具影响力的任务。本文提出了一种用于VSR的循环反投影生成对抗网络（RBPGAN），旨在生成时间一致性解决方案的同时保留空间细节。RBPGAN融合了两种最先进的模型，在不影响生成视频精度的前提下兼顾两者的优势。该模型的生成器受RBPN系统启发，而判别器则借鉴了TecoGAN。我们还利用乒乓损失（Ping-Pong loss）来增强时间维度上的连贯性。通过在不同数据集上进行的定性与定量实验，我们证明该贡献共同形成的模型在时间一致性细节方面优于先前的工作。