mlsanityData to 7 Oct 2026

Exploiting Aliasing for Manga Restoration

arXiv 2105.06830 ↗First posted 14 May 2021eess.IV cs.CVcited by 10

Not on the map. Why?

Abstract (arXiv)

As a popular entertainment art form, manga enriches the line drawings details with bitonal screentones. However, manga resources over the Internet usually show screentone artifacts because of inappropriate scanning/rescaling resolution. In this paper, we propose an innovative two-stage method to restore quality bitonal manga from degraded ones. Our key observation is that the aliasing induced by downsampling bitonal screentones can be utilized as informative clues to infer the original resolution and screentones. First, we predict the target resolution from the degraded manga via the Scale Estimation Network (SE-Net) with spatial voting scheme. Then, at the target resolution, we restore the region-wise bitonal screentones via the Manga Restoration Network (MR-Net) discriminatively, depending on the degradation degree. Specifically, the original screentones are directly restored in pattern-identifiable regions, and visually plausible screentones are synthesized in pattern-agnostic regions. Quantitative evaluation on synthetic data and visual assessment on real-world cases illustrate the effectiveness of our method.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 19 of its 30 references that are in the map. First posted on arXiv 14 May 2021.

Builds on

19 of 30 references.

References · 19

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,590
  3. 2018CBAM: Convolutional Block Attention Modulecited by 2,463
  4. 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,385
  5. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,898
  6. 2017Enhanced Deep Residual Networks for Single Image Super-Resolutioncited by 1,543
  7. 2018ESRGAN: Enhanced Super-Resolution Generative Adversarial Networkscited by 1,250
  8. 2014Image Super-Resolution Using Deep Convolutional Networkscited by 1,218
  9. 2015Accurate Image Super-Resolution Using Very Deep Convolutional Networkscited by 902
  10. 2017Learning Deep CNN Denoiser Prior for Image Restorationcited by 407
  11. 2017Residual Attention Network for Image Classificationcited by 385
  12. 2019Deep Learning for Image Super-resolution: A Surveycited by 368
7 more
  1. 2018Scale-recurrent Network for Deep Image Deblurringcited by 332
  2. 2015Sketch-based Manga Retrieval using Manga109 Datasetcited by 326
  3. 2019Meta-SR: A Magnification-Arbitrary Network for Super-Resolutioncited by 180
  4. 2018Non-Local Recurrent Network for Image Restorationcited by 160
  5. 2017Fast and Accurate Image Super-Resolution with Deep Laplacian Pyramid Networkscited by 138
  6. 2015Compression Artifacts Reduction by a Deep Convolutional Networkcited by 136
  7. 2018Image Super-Resolution via Deterministic-Stochastic Synthesis and Local Statistical Rectificationcited by 2

Built on by

Cited by year

Citing papers per year: 2021: 2; 2022: 3; 2023: 3; 2024: 1; 2025: 1.

10 papers.

  1. 2023Picture that Sketch: Photorealistic Image Generation from Abstract Sketchescited by 34
  2. 2021SketchEdit: Mask-Free Local Image Manipulation with Partial Sketchescited by 32
  3. 2022Doodle It Yourself: Class Incremental Learning by Drawing a Few Sketchescited by 23
  4. 2023What Can Human Sketches Do for Object Detection?cited by 19
  5. 2023Sketch2Saliency: Learning to Detect Salient Objects from Human Drawingscited by 17
  6. 2021MARVEL: Raster Manga Vectorization via Primitive-wise Deep Reinforcement Learningcited by 2
  7. 2024Sketch2Manga: Shaded Manga Screening from Sketch with Diffusion Modelscited by 2
  8. 2022Towards Practicality of Sketch-Based Visual Understandingcited by 1
  9. 2022Screentone-Preserved Manga Retargetingcited by 0
  10. 2025Doodle Your Keypoints: Sketch-Based Few-Shot Keypoint Detectioncited by 0