Video super-resolution (VSR) is a prominent research topic in low-level computer vision, where deep learning technologies have played a significant role. The rapid progress in deep learning and its applications in VSR has led to a proliferation of tools and techniques in the literature. However, the usage of these methods is often not adequately explained, and decisions are primarily driven by quantitative improvements. Given the significance of VSR’s potential influence across multiple domains, it is imperative to conduct a comprehensive analysis of the elements and deep learning methodologies employed in VSR research. This methodical analysis will facilitate the informed development of models tailored to specific application needs. In this paper, we present a comprehensive overview of deep learning-based video super-resolution models, investigating each component and discussing its implications. Furthermore, we provide a synopsis of key components and technologies employed by state-of-the-art and earlier VSR models. By elucidating the underlying methodologies and categorising them systematically, we identified trends, requirements, and challenges in the domain. As a first-of-its-kind comprehensive overview of deep learning-based VSR models, this work also establishes a multi-level taxonomy to guide current and future VSR research, enhancing the maturation and interpretation of VSR practices for various practical applications.

This paper presents a novel approach to video super-resolution (VSR) by focusing on the selection of input frames, a process critical to VSR. VSR methods typically rely on deep learning techniques, those that are able to learn features from a large dataset of low-resolution (LR) and corresponding high-resolution (HR) videos and generate high-quality HR frames from any new LR input frames using the learned features. However, these methods often use as input the immediate neighbouring frames to a given target frame without considering the importance and dynamics of the frames across the temporal dimension of a video. This work aims to address the limitations of the conventional sliding-window mechanisms by developing input frame selection algorithms. By dynamically selecting the most representative neighbouring frames based on content-aware selection measures, our proposed algorithms enable VSR models to extract more informative and accurate features that are better aligned with the target frame, leading to improved performance and higher-quality HR frames. Through an empirical study, we demonstrate that the proposed dynamic content-aware selection mechanism improves super-resolution results without any additional architectural overhead, offering a counter-intuitive yet effective alternative to the long-established trend of increasing architectural complexity to improve VSR results.

Omnidirectional Videos (or 360° videos) are widely used in Virtual Reality (VR) to facilitate immersive and interactive viewing experiences. However, the limited spatial resolution in 360° videos does not allow for each degree of view to be represented with adequate pixels, limiting the visual quality offered in the immersive experience. Deep learning Video Super-Resolution (VSR) techniques used for conventional videos could provide a promising software-based solution; however, these techniques do not tackle the distortion present in equirectangular projections of 360° video signals. An additional obstacle is the limited 360° video datasets to study. To address these issues, this paper creates a novel 360° Video Dataset (360VDS) with a study of the extensibility of conventional VSR models to 360° videos. This paper further proposes a novel deep learning model for 360° Video Super-Resolution (360° VSR), called Spherical Signal Super-resolution with a Proportioned Optimisation (S3PO). S3PO adopts recurrent modelling with an attention mechanism, unbound from conventional VSR techniques like alignment. With a purpose-built feature extractor and a novel loss function addressing spherical distortion, S3PO outperforms most state-of-the-art conventional VSR models and 360° specific super-resolution models on 360° video datasets. A step-wise ablation study is presented to understand and demonstrate the impact of the chosen architectural subcomponents, targeted training and optimisation.

This is an original research article entitled “Online Video Super-Resolution using Unidirectional Recurrent Model”. Considering the critical constraints around video frames and resource availability in an online setting, this paper presents a new unidirectional video super-resolution (VSR) model with a recurrent architecture specifically designed for online applications. Many recent works in the video super-resolution domain focus on improving the super-resolution quality at the cost of computationally intense and input-heavy bidirectional modelling. To alleviate these drawbacks, we propose the Replenished Recurrency with Dual-Duct (R2D2) model which adopts unidirectional architecture to fully utilise local features and global memory available at each timestamp. The two variants – R2D2 and R2D2-lite presented in the paper generate state-of-the-art super-resolution quality at significantly optimised efficiency. This is believed an important step forward in real-world applications-inspired research in the video super-resolution domain.