• Corpus ID: 245144957

Raw Bayer Pattern Image Synthesis for Computer Vision-oriented Image Signal Processing Pipeline Design

@inproceedings{Zhou2021RawBP,
  title={Raw Bayer Pattern Image Synthesis for Computer Vision-oriented Image Signal Processing Pipeline Design},
  author={Wei Zhou and Xiangyu Zhang and Hongyu Wang and Shenghua Gao and Xin Lou},
  year={2021}
}
  • Wei Zhou, Xiangyu Zhang, +2 authors Xin Lou
  • Published 25 October 2021
  • Engineering, Computer Science
In this paper, we propose a method to add constraints that are un-formulatable in generative adversarial networks (GAN)-based arbitrary size RAW Bayer image generation. It is shown theoretically that by using the transformed data in GAN training, it is able to improve the learning of the original data distribution, owing to the invariant of Jensen–Shannon (JS) divergence between two distributions under invertible and differentiable transformation. Benefiting from the proposed method, RAW Bayer… 

Figures and Tables from this paper

References

SHOWING 1-10 OF 47 REFERENCES
Saliency Map-Aided Generative Adversarial Network for RAW to RGB Mapping
TLDR
Experimental results show that the proposed general transformation method for cross-camera RAW to RGB mapping based on Generative Adversarial Network (GAN) can generate more clear and visually plausible images than state-of-the-art networks.
Analyzing and Improving the Image Quality of StyleGAN
TLDR
This work redesigns the generator normalization, revisit progressive growing, and regularize the generator to encourage good conditioning in the mapping from latent codes to images, and thereby redefines the state of the art in unconditional image modeling.
High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs
TLDR
A new method for synthesizing high-resolution photo-realistic images from semantic label maps using conditional generative adversarial networks (conditional GANs) is presented, which significantly outperforms existing methods, advancing both the quality and the resolution of deep image synthesis and editing.
FlexISP: a flexible camera image processing framework
  • K. Pulli
  • Computer Science
    ACM Trans. Graph.
  • 2014
TLDR
This work proposes an end-to-end system that is aware of the camera and image model, enforces natural-image priors, while jointly accounting for common image processing steps like demosaicking, denoising, deconvolution, and so forth, all directly in a given output representation.
AIM 2019 Challenge on RAW to RGB Mapping: Methods and Results
TLDR
This paper reviews the first AIM challenge on mapping camera RAW toRGB images with the focus on proposed solutions and results, defining the state-of-the-art for RAW to RGB image restoration.
Reconfiguring the Imaging Pipeline for Computer Vision
TLDR
This work examines the role of the image signal processing (ISP) pipeline in computer vision to identify opportunities to reduce computation and save energy, and proposes a new image sensor design that can compensate for these stages.
Image-to-Image Translation with Conditional Adversarial Networks
TLDR
Conditional adversarial networks are investigated as a general-purpose solution to image-to-image translation problems and it is demonstrated that this approach is effective at synthesizing photos from label maps, reconstructing objects from edge maps, and colorizing images, among other tasks.
Neural Network Generalization: The Impact of Camera Parameters
TLDR
It is found that pixel size impacts generalization, demosaicking substantially impacts performance and generalization for shallow (8-bit) bit-depths but not deeper ones (10-bit), and the network performs well using raw (not demosaicked) sensor data for 10-bit pixels.
Minimalistic Image Signal Processing for Deep Learning Applications
TLDR
To make in-sensor accelerators practical, energy-efficient operations that yield most of the benefits of an ISP and reduce covariate shift between the training (ISP processed images) and target (RAW images) distributions are described.
Hybrid color filter array demosaicking for effective artifact suppression
TLDR
A new CFA demosaicking algorithm is composed to suppress as many demosaicks artifacts as possible and obtain full-color images of high quality and outperforms the existing state-of-the-art methods both visually and in terms of peak signal-to-noise ratio.
...
1
2
3
4
5
...