iSeeBetter: Spatio-temporal video super-resolution using recurrent generative back-projection networks

TL;DR

iSeeBetter is a GAN-based spatio-temporal video super-resolution method that leverages recurrent back-projection networks to produce temporally consistent, high-quality videos with improved naturalness and detail, surpassing existing methods.

Contribution

The paper introduces iSeeBetter, a novel GAN-based VSR approach that incorporates recurrent back-projection networks and a multi-component loss function for superior performance.

Findings

Outperforms state-of-the-art VSR methods in fidelity.

Produces temporally consistent super-resolved videos.

Enhances naturalness and detail in super-resolved frames.

Abstract

Recently, learning-based models have enhanced the performance of single-image super-resolution (SISR). However, applying SISR successively to each video frame leads to a lack of temporal coherency. Convolutional neural networks (CNNs) outperform traditional approaches in terms of image quality metrics such as peak signal to noise ratio (PSNR) and structural similarity (SSIM). However, generative adversarial networks (GANs) offer a competitive advantage by being able to mitigate the issue of a lack of finer texture details, usually seen with CNNs when super-resolving at large upscaling factors. We present iSeeBetter, a novel GAN-based spatio-temporal approach to video super-resolution (VSR) that renders temporally consistent super-resolution videos. iSeeBetter extracts spatial and temporal information from the current and neighboring frames using the concept of recurrent back-projection networks as its generator. Furthermore, to improve the "naturality" of the super-resolved image while eliminating artifacts seen with traditional algorithms, we utilize the discriminator from super-resolution generative adversarial network (SRGAN). Although mean squared error (MSE) as a primary loss-minimization objective improves PSNR/SSIM, these metrics may not capture fine details in the image resulting in misrepresentation of perceptual quality. To address this, we use a four-fold (MSE, perceptual, adversarial, and total-variation (TV)) loss function. Our results demonstrate that iSeeBetter offers superior VSR fidelity and surpasses state-of-the-art performance.