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

arXiv: https://arxiv.org/abs/2207.07795 · HTML: https://mlsanity.com/paper/2207.07795/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 48 references that are in the map.
- First posted on arXiv 16 Jul 2022.

## Builds on (most cited first, 13 of 13)

- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising](https://mlsanity.com/paper/1608.03981/) (2016)
- [Multi-Scale Context Aggregation by Dilated Convolutions](https://mlsanity.com/paper/1511.07122/) (2015)
- [An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition](https://mlsanity.com/paper/1507.05717/) (2015)
- [Noise2Self: Blind Denoising by Self-Supervision](https://mlsanity.com/paper/1901.11365/) (2019)
- [Toward Convolutional Blind Denoising of Real Photographs](https://mlsanity.com/paper/1807.04686/) (2018)
- [Attentive Generative Adversarial Network for Raindrop Removal from a Single Image](https://mlsanity.com/paper/1711.10098/) (2017)
- [Heavy Rain Image Restoration: Integrating Physics Model and Conditional Adversarial Learning](https://mlsanity.com/paper/1904.05050/) (2019)
- [Invertible Denoising Network: A Light Solution for Real Noise Removal](https://mlsanity.com/paper/2104.10546/) (2021)
- [Noise2Same: Optimizing A Self-Supervised Bound for Image Denoising](https://mlsanity.com/paper/2010.11971/) (2020)
- [Physics-Based Generative Adversarial Models for Image Restoration and Beyond](https://mlsanity.com/paper/1808.00605/) (2018)
- [GRDN:Grouped Residual Dense Network for Real Image Denoising and GAN-based Real-world Noise Modeling](https://mlsanity.com/paper/1905.11172/) (2019)

## Built on by (most cited first, 12 of 12)

- [Toward Zero-shot Character Recognition: A Gold Standard Dataset with Radical-level Annotations](https://mlsanity.com/paper/2308.00655/) (2023)
- [Edge Guided GANs with Multi-Scale Contrastive Learning for Semantic Image Synthesis](https://mlsanity.com/paper/2307.12084/) (2023)
- [Ancient Script Image Recognition and Processing: A Review](https://mlsanity.com/paper/2506.19208/) (2025)
- [WuYun: Exploring hierarchical skeleton-guided melody generation using knowledge-enhanced deep learning](https://mlsanity.com/paper/2301.04488/) (2023)
- [Mitigating Long-tail Distribution in Oracle Bone Inscriptions: Dataset, Model, and Benchmark](https://mlsanity.com/paper/2504.09555/) (2025)
- [Reviving Cultural Heritage: A Novel Approach for Comprehensive Historical Document Restoration](https://mlsanity.com/paper/2507.05108/) (2025)
- [OBIFormer: A Fast Attentive Denoising Framework for Oracle Bone Inscriptions](https://mlsanity.com/paper/2504.13524/) (2025)
- [InteChar: A Unified Oracle Bone Character List for Ancient Chinese Language Modeling](https://mlsanity.com/paper/2508.15791/) (2025)
- [AncientBench: Towards Comprehensive Evaluation on Excavated and Transmitted Chinese Corpora](https://mlsanity.com/paper/2512.17756/) (2025)
- [Knowledge-Aware Artifact Image Synthesis with LLM-Enhanced Prompting and Multi-Source Supervision](https://mlsanity.com/paper/2312.08056/) (2023)
- [Towards Computational Chinese Paleography](https://mlsanity.com/paper/2601.06753/) (2026)
- [Logographic Character Visual Pretraining via Semantic-based Contrastive Learning](https://mlsanity.com/paper/2608.00096/) (2026)

## Abstract (arXiv)

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.