Expanding Synthetic Real-World Degradations for Blind Video Super Resolution

TL;DR

This paper enhances blind video super-resolution by synthesizing realistic degradations on training data, leading to improved performance and introducing a new real-world video dataset for benchmarking.

Contribution

It proposes a novel method to simulate real-world degradations on synthetic datasets and trains a deep neural network with this diverse data, improving super-resolution results.

Findings

Performance improved by 7.1% in NRQM over RealBasicVSR.

Achieved 3.34% higher NRQM than BSRGAN.

Introduced a new high-resolution real-world video dataset.

Abstract

Video super-resolution (VSR) techniques, especially deep-learning-based algorithms, have drastically improved over the last few years and shown impressive performance on synthetic data. However, their performance on real-world video data suffers because of the complexity of real-world degradations and misaligned video frames. Since obtaining a synthetic dataset consisting of low-resolution (LR) and high-resolution (HR) frames are easier than obtaining real-world LR and HR images, in this paper, we propose synthesizing real-world degradations on synthetic training datasets. The proposed synthetic real-world degradations (SRWD) include a combination of the blur, noise, downsampling, pixel binning, and image and video compression artifacts. We then propose using a random shuffling-based strategy to simulate these degradations on the training datasets and train a single end-to-end deep neural network (DNN) on the proposed larger variation of realistic synthesized training data. Our quantitative and qualitative comparative analysis shows that the proposed training strategy using diverse realistic degradations improves the performance by 7.1 % in terms of NRQM compared to RealBasicVSR and by 3.34 % compared to BSRGAN on the VideoLQ dataset. We also introduce a new dataset that contains high-resolution real-world videos that can serve as a common ground for bench-marking.