A Single-Frame and Multi-Frame Cascaded Image Super-Resolution Method

TL;DR

This paper introduces a novel cascaded super-resolution approach combining multi-frame and single-frame methods, utilizing an L0-norm constrained scheme and residual back-projection to enhance image quality in both simulated and real-world scenarios.

Contribution

It proposes a two-step cascaded super-resolution method that integrates variational models with deep learning, improving performance and robustness over existing techniques.

Findings

Achieved higher PSNR scores on benchmark datasets.

Demonstrated superior perceptual quality in reconstructed images.

Proved robustness across different super-resolution methods.

Abstract

The objective of image super-resolution is to reconstruct a high-resolution (HR) image with the prior knowledge from one or several low-resolution (LR) images. However, in the real world, due to the limited complementary information, the performance of both single-frame and multi-frame super-resolution reconstruction degrades rapidly as the magnification increases. In this paper, we propose a novel two-step image super resolution method concatenating multi-frame super-resolution (MFSR) with single-frame super-resolution (SFSR), to progressively upsample images to the desired resolution. The proposed method consisting of an L0-norm constrained reconstruction scheme and an enhanced residual back-projection network, integrating the flexibility of the variational modelbased method and the feature learning capacity of the deep learning-based method. To verify the effectiveness of the proposed algorithm, extensive experiments with both simulated and real world sequences were implemented. The experimental results show that the proposed method yields superior performance in both objective and perceptual quality measurements. The average PSNRs of the cascade model in set5 and set14 are 33.413 dB and 29.658 dB respectively, which are 0.76 dB and 0.621 dB more than the baseline method. In addition, the experiment indicates that this cascade model can be robustly applied to different SFSR and MFSR methods.