Towards Efficient and Scale-Robust Ultra-High-Definition Image Demoireing

TL;DR

This paper introduces a new ultra-high-definition demoireing dataset and a lightweight model that effectively removes moire patterns from 4K images, outperforming existing methods.

Contribution

The paper presents the first UHD demoireing dataset and a novel efficient model with a semantic-aligned scale-aware module for 4K image moire removal.

Findings

Our dataset contains 5,000 real-world 4K image pairs.

The proposed ESDNet outperforms state-of-the-art methods significantly.

Our approach is more lightweight and effective for ultra-high-definition images.

Abstract

With the rapid development of mobile devices, modern widely-used mobile phones typically allow users to capture 4K resolution (i.e., ultra-high-definition) images. However, for image demoireing, a challenging task in low-level vision, existing works are generally carried out on low-resolution or synthetic images. Hence, the effectiveness of these methods on 4K resolution images is still unknown. In this paper, we explore moire pattern removal for ultra-high-definition images. To this end, we propose the first ultra-high-definition demoireing dataset (UHDM), which contains 5,000 real-world 4K resolution image pairs, and conduct a benchmark study on current state-of-the-art methods. Further, we present an efficient baseline model ESDNet for tackling 4K moire images, wherein we build a semantic-aligned scale-aware module to address the scale variation of moire patterns. Extensive experiments manifest the effectiveness of our approach, which outperforms state-of-the-art methods by a large margin while being much more lightweight. Code and dataset are available at https://xinyu-andy.github.io/uhdm-page.