RCRN: Real-world Character Image Restoration Network via Skeleton Extraction

TL;DR

This paper introduces RCRN, a novel network that restores degraded real-world character images by leveraging skeleton extraction and scale-ensemble features, addressing unique noise challenges.

Contribution

The paper proposes a new network architecture combining skeleton extraction and scale-ensemble features for effective real-world character image restoration.

Findings

RCRN outperforms existing methods quantitatively.

Constructed a new dataset with real-world degraded character images.

Demonstrated improved restoration quality both visually and numerically.

Abstract

Constructing high-quality character image datasets is challenging because real-world images are often affected by image degradation. There are limitations when applying current image restoration methods to such real-world character images, since (i) the categories of noise in character images are different from those in general images; (ii) real-world character images usually contain more complex image degradation, e.g., mixed noise at different noise levels. To address these problems, we propose a real-world character restoration network (RCRN) to effectively restore degraded character images, where character skeleton information and scale-ensemble feature extraction are utilized to obtain better restoration performance. The proposed method consists of a skeleton extractor (SENet) and a character image restorer (CiRNet). SENet aims to preserve the structural consistency of the character and normalize complex noise. Then, CiRNet reconstructs clean images from degraded character images and their skeletons. Due to the lack of benchmarks for real-world character image restoration, we constructed a dataset containing 1,606 character images with real-world degradation to evaluate the validity of the proposed method. The experimental results demonstrate that RCRN outperforms state-of-the-art methods quantitatively and qualitatively.