Cuboid-Net: A Multi-Branch Convolutional Neural Network for Joint Space-Time Video Super Resolution

TL;DR

Cuboid-Net is a novel multi-branch CNN that enhances both spatial and temporal resolutions of low-resolution videos by treating videos as cuboids, effectively exploiting spatio-temporal information for super-resolution.

Contribution

The paper introduces Cuboid-Net, a multi-branch CNN architecture that jointly improves spatial and temporal resolution by processing videos as cuboids with directional slices.

Findings

Effective in spatial and temporal super-resolution of videos

Improves spatial and angular super-resolution of light field data

Outperforms existing methods in quality enhancement

Abstract

The demand for high-resolution videos has been consistently rising across various domains, propelled by continuous advancements in science, technology, and societal. Nonetheless, challenges arising from limitations in imaging equipment capabilities, imaging conditions, as well as economic and temporal factors often result in obtaining low-resolution images in particular situations. Space-time video super-resolution aims to enhance the spatial and temporal resolutions of low-resolution and low-frame-rate videos. The currently available space-time video super-resolution methods often fail to fully exploit the abundant information existing within the spatio-temporal domain. To address this problem, we tackle the issue by conceptualizing the input low-resolution video as a cuboid structure. Drawing on this perspective, we introduce an innovative methodology called "Cuboid-Net," which incorporates a multi-branch convolutional neural network. Cuboid-Net is designed to collectively enhance the spatial and temporal resolutions of videos, enabling the extraction of rich and meaningful information across both spatial and temporal dimensions. Specifically, we take the input video as a cuboid to generate different directional slices as input for different branches of the network. The proposed network contains four modules, i.e., a multi-branch-based hybrid feature extraction (MBFE) module, a multi-branch-based reconstruction (MBR) module, a first stage quality enhancement (QE) module, and a second stage cross frame quality enhancement (CFQE) module for interpolated frames only. Experimental results demonstrate that the proposed method is not only effective for spatial and temporal super-resolution of video but also for spatial and angular super-resolution of light field.