Deep Photo Scan: Semi-Supervised Learning for dealing with the real-world degradation in Smartphone Photo Scanning

@article{Ho2022DeepPS,
  title={Deep Photo Scan: Semi-Supervised Learning for dealing with the real-world degradation in Smartphone Photo Scanning},
  author={Man M. Ho and Jinjia Zhou},
  journal={2022 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)},
  year={2022},
  pages={894-903}
}
  • Man M. Ho, Jinjia Zhou
  • Published 11 February 2021
  • Computer Science
  • 2022 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)
Physical photographs now can be conveniently scanned by smartphones and stored forever as digital images, yet the scanned photos are not restored well. One solution is to train a supervised deep neural network on many digital images and their smartphone-scanned versions. However, it requires a high labor cost, leading to limited training data. Previous works create training pairs by simulating degradation using low-level image processing techniques. Their synthetic images are then formed with… 

References

SHOWING 1-10 OF 56 REFERENCES
DSLR-Quality Photos on Mobile Devices with Deep Convolutional Networks
TLDR
An end-to-end deep learning approach that bridges the gap by translating ordinary photos into DSLR-quality images by learning the translation function using a residual convolutional neural network that improves both color rendition and image sharpness.
Old Photo Restoration via Deep Latent Space Translation
  • Ziyu Wan, Bo Zhang, Fang Wen
  • Computer Science
    IEEE transactions on pattern analysis and machine intelligence
  • 2022
TLDR
A novel triplet domain translation network is proposed by leveraging real photos along with massive synthetic image pairs to transform old photos and clean photos into two latent spaces, leading to improved capability to restore old photos from multiple defects.
Bringing Old Photos Back to Life
  • Ziyu Wan, Bo Zhang, Fang Wen
  • Computer Science
    2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2020
TLDR
A novel triplet domain translation network by leveraging real photos along with massive synthetic image pairs to restore old photos that suffer from severe degradation through a deep learning approach outperforms state-of-the-art methods in terms of visual quality.
A High-Quality Denoising Dataset for Smartphone Cameras
TLDR
This paper proposes a systematic procedure for estimating ground truth for noisy images that can be used to benchmark denoising performance for smartphone cameras and shows that CNN-based methods perform better when trained on the authors' high-quality dataset than when trained using alternative strategies, such as low-ISO images used as a proxy for ground truth data.
Semi-Supervised Learning for Few-Shot Image-to-Image Translation
TLDR
This work proposes applying semi-supervised learning via a noise-tolerant pseudo-labeling procedure, and applies a cycle consistency constraint to further exploit the information from unlabeled images, either from the same dataset or external.
Perceptual Losses for Real-Time Style Transfer and Super-Resolution
TLDR
This work considers image transformation problems, and proposes the use of perceptual loss functions for training feed-forward networks for image transformation tasks, and shows results on image style transfer, where aFeed-forward network is trained to solve the optimization problem proposed by Gatys et al. in real-time.
Benchmarking Denoising Algorithms with Real Photographs
  • Tobias Plötz, S. Roth
  • Computer Science
    2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2017
TLDR
This work develops a methodology for benchmarking denoising techniques on real photographs, and captures pairs of images with different ISO values and appropriately adjusted exposure times, where the nearly noise-free low-ISO image serves as reference.
Zoom to Learn, Learn to Zoom
TLDR
This paper shows that when applying machine learning to digital zoom, it is beneficial to operate on real, RAW sensor data, and shows how to obtain such ground-truth data via optical zoom and contribute a dataset, SR-RAW, for real-world computational zoom.
Deep Preset: Blending and Retouching Photos with Color Style Transfer
  • Man M. Ho, Jinjia Zhou
  • Computer Science
    2021 IEEE Winter Conference on Applications of Computer Vision (WACV)
  • 2021
TLDR
This work proposes a color style transfer named Deep Preset designed to generalize the features representing the color transformation from content with natural colors to retouched reference, then blend it into the contextual features of content, then predict hyper-parameters (settings or preset) of the applied low-level color transformation methods.
Feedback Network for Image Super-Resolution
TLDR
An image super-resolution feedback network (SRFBN) is proposed to refine low-level representations with high-level information by using hidden states in a recurrent neural network (RNN) with constraints to achieve such feedback manner.
...
...