Improving Generative Adversarial Networks for Video Super-Resolution

TL;DR

This paper investigates techniques to enhance GAN-based video super-resolution, demonstrating significant improvements in image quality metrics through temporal smoothing, LSTM layers, and a temporal loss function.

Contribution

The study introduces effective methods like temporal smoothing, LSTM layers, and a temporal loss function to improve GAN performance in video super-resolution tasks.

Findings

11.97% PSNR improvement over baseline

8% SSIM enhancement compared to baseline

Effective techniques include temporal smoothing and LSTM layers

Abstract

In this research, we explore different ways to improve generative adversarial networks for video super-resolution tasks from a base single image super-resolution GAN model. Our primary objective is to identify potential techniques that enhance these models and to analyze which of these techniques yield the most significant improvements. We evaluate our results using Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM). Our findings indicate that the most effective techniques include temporal smoothing, long short-term memory (LSTM) layers, and a temporal loss function. The integration of these methods results in an 11.97% improvement in PSNR and an 8% improvement in SSIM compared to the baseline video super-resolution generative adversarial network (GAN) model. This substantial improvement suggests potential further applications to enhance current state-of-the-art models.