In many applications, including surveillance, entertainment, and restoration, there is a need to increase both the spatial resolution and the frame rate of a video sequence. The aim is to improve visual quality, refine details, and create a more realistic viewing experience. Existing space-time video super-resolution methods do not effectively use spatio-temporal information. To address this limitation, we propose a generative adversarial network for joint space-time video super-resolution. The generative network consists of three operations: shallow feature extraction, deep feature extraction, and reconstruction. It uses three-dimensional (3D) convolutions to process temporal and spatial information simultaneously and includes a novel 3D attention mechanism to extract the most important channel and spatial information. The discriminative network uses a two-branch structure to handle details and motion information, making the generated results more accurate. Experimental results on the Vid4, Vimeo-90K, and REDS datasets demonstrate the effectiveness of the proposed method. The source code is publicly available at https://github.com/FCongRui/3DAttGan.git.
@article{arxiv.2407.16965,
title = {3DAttGAN: A 3D Attention-based Generative Adversarial Network for Joint Space-Time Video Super-Resolution},
author = {Congrui Fu and Hui Yuan and Liquan Shen and Raouf Hamzaoui and Hao Zhang},
journal= {arXiv preprint arXiv:2407.16965},
year = {2024}
}