Papers
Topics
Authors
Recent
2000 character limit reached

AADNet: Attention aware Demoiréing Network

Published 13 Mar 2024 in cs.CV | (2403.08384v2)

Abstract: Moire pattern frequently appears in photographs captured with mobile devices and digital cameras, potentially degrading image quality. Despite recent advancements in computer vision, image demoire'ing remains a challenging task due to the dynamic textures and variations in colour, shape, and frequency of moire patterns. Most existing methods struggle to generalize to unseen datasets, limiting their effectiveness in removing moire patterns from real-world scenarios. In this paper, we propose a novel lightweight architecture, AADNet (Attention Aware Demoireing Network), for high-resolution image demoire'ing that effectively works across different frequency bands and generalizes well to unseen datasets. Extensive experiments conducted on the UHDM dataset validate the effectiveness of our approach, resulting in high-fidelity images.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (20)
  1. Learning to see in the dark.
  2. Qifeng Chen and Vladlen Koltun. 2017. Photographic image synthesis with cascaded refinement networks.
  3. Multi-scale dynamic feature encoding network for image demoireing.
  4. Generative adversarial networks.
  5. Mop moire patterns using mopnet. In ICCV, pages 2424–2432.
  6. Fhde2net: Full high definition demoireing network. In European Conference on Computer Vision.
  7. Focal frequency loss for image reconstruction and synthesis.
  8. Perceptual losses for real-time style transfer and super-resolution.
  9. Demoiréing of camera-captured screen images using deep convolutional neural network.
  10. Full-resolution residual networks for semantic segmentation in street scenes.
  11. U-net: Convolutional networks for biomedical image segmentation.
  12. Moiré photo restoration using multiresolution convolutional neural networks. IEEE Transactions on Image Processing, 27(8):4160–4172.
  13. Attention is all you need.
  14. Deep high-resolution representation learning for visual recognition.
  15. Semantic image inpainting with perceptual and contextual losses. ArXiv, abs/1607.07539.
  16. Towards efficient and scale-robust ultra-high-definition image demoiréing. In European Conference on Computer Vision, pages 646–662. Springer.
  17. Aim 2019 challenge on image demoireing: Methods and results.
  18. The unreasonable effectiveness of deep features as a perceptual metric. In CVPR.
  19. Image demoireing with learnable bandpass filters.
  20. Stereo magnification: Learning view synthesis using multiplane images.

Summary

Paper to Video (Beta)

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Continue Learning

We haven't generated follow-up questions for this paper yet.

Collections

Sign up for free to add this paper to one or more collections.

Tweets

Sign up for free to view the 1 tweet with 0 likes about this paper.