Implicit Transformer Network for Screen Content Image Continuous Super-Resolution

TL;DR

This paper introduces a novel Implicit Transformer Super-Resolution Network (ITSRN) tailored for screen content images, enabling high-quality continuous super-resolution at arbitrary scales, outperforming existing methods especially for compressed and uncompressed SCIs.

Contribution

The paper proposes a new implicit transformer-based network with an implicit position encoding scheme for continuous super-resolution of screen content images, addressing the limitations of natural image SR methods.

Findings

ITSRN significantly outperforms existing SR methods on SCI datasets.

The model effectively handles both compressed and uncompressed SCIs.

Constructed benchmark datasets SCI1K and SCI1K-compression for evaluation.

Abstract

Nowadays, there is an explosive growth of screen contents due to the wide application of screen sharing, remote cooperation, and online education. To match the limited terminal bandwidth, high-resolution (HR) screen contents may be downsampled and compressed. At the receiver side, the super-resolution (SR) of low-resolution (LR) screen content images (SCIs) is highly demanded by the HR display or by the users to zoom in for detail observation. However, image SR methods mostly designed for natural images do not generalize well for SCIs due to the very different image characteristics as well as the requirement of SCI browsing at arbitrary scales. To this end, we propose a novel Implicit Transformer Super-Resolution Network (ITSRN) for SCISR. For high-quality continuous SR at arbitrary ratios, pixel values at query coordinates are inferred from image features at key coordinates by the proposed implicit transformer and an implicit position encoding scheme is proposed to aggregate similar neighboring pixel values to the query one. We construct benchmark SCI1K and SCI1K-compression datasets with LR and HR SCI pairs. Extensive experiments show that the proposed ITSRN significantly outperforms several competitive continuous and discrete SR methods for both compressed and uncompressed SCIs.