Home Research Papers Datasets State of the Art Pricing

Discover, visualize, and connect AI research papers. Explore the latest trends and insights in artificial intelligence research.

Product

Home
Research Papers
About

Support

Contact
Terms of Service
Privacy Policy

© 2026 Papersgraph. All rights reserved.

computer-vision-3

Demosaicking

3260 papers • 126 benchmarks • 313 datasets

Most modern digital cameras acquire color images by measuring only one color channel per pixel, red, green, or blue, according to a specific pattern called the Bayer pattern. Demosaicking is the processing step that reconstruct a full color image given these incomplete measurements. Source: Revisiting Non Local Sparse Models for Image Restoration

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in demosaicking-3

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

i

Use these libraries to find demosaicking-3 models and implementations

Datasets

PixelShift200

Subtasks

No subtasks available.

Most implemented papers

Plug-and-Play Image Restoration With Deep Denoiser Prior

K. Zhang, W. Zuo, L. Gool, Radu Timofte, Yawei Li, Lei Zhang•Sun Aug 30 2020

Experimental results demonstrate that the proposed plug-and-play image restoration with deep denoiser prior not only significantly outperforms other state-of-the-art model-based methods but also achieves competitive or even superior performance against state- of theart learning- based methods.

1052

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

0

Handheld multi-frame super-resolution

P. Milanfar, Chia-Kai Liang, Bartlomiej Wronski, Ignacio Garcia-Dorado, M. Ernst, D. Kelly, Michael Krainin, M. Levoy•Tue May 07 2019

A multiframe super-resolution algorithm that creates a complete RGB image directly from a burst of CFA raw images, which is the basis of the Super-Res Zoom feature, as well as the default merge method in Night Sight mode on Google's flagship phone.

221 0

CURL: Neural Curve Layers for Global Image Enhancement

G. Slabaugh, S. Moran, Steven G. McDonagh•Thu Nov 28 2019

We present a novel approach to adjust global image properties such as colour, saturation, and luminance using human-interpretable image enhancement curves, inspired by the Photoshop curves tool. Our method, dubbed neural CURve Layers (CURL), is designed as a multi-colour space neural retouching block trained jointly in three different colour spaces (HSV, CIELab, RGB) guided by a novel multi-colour space loss. The curves are fully differentiable and are trained end-to-end for different computer vision problems including photo enhancement (RGB-to-RGB) and as part of the image signal processing pipeline for image formation (RAW-to-RGB). To demonstrate the effectiveness of CURL we combine this global image transformation block with a pixel-level (local) image multi-scale encoder-decoder backbone network. In an extensive experimental evaluation we show that CURL produces state-of-the-art image quality versus recently proposed deep learning approaches in both objective and perceptual metrics, setting new state-of-the-art performance on multiple public datasets. Our code is publicly available at: https://github.com/sjmoran/CURL.

71 0

Replacing Mobile Camera ISP with a Single Deep Learning Model

L. Gool, Radu Timofte, Andrey D. Ignatov•Wed Feb 12 2020

PyNET is presented, a novel pyramidal CNN architecture designed for fine-grained image restoration that implicitly learns to perform all ISP steps such as image demosaicing, denoising, white balancing, color and contrast correction, demoireing, etc.

200 0

Residual Non-local Attention Networks for Image Restoration

Y. Fu, Kunpeng Li, Yulun Zhang, Kai Li, Bineng Zhong•Thu Feb 28 2019

The proposed residual local and non-local attention learning to train the very deep network is generalized for various image restoration applications, such as image denoising, demosaicing, compression artifacts reduction, and super-resolution.

751 0

Pyramid Attention Networks for Image Restoration

Ding Liu, Thomas S. Huang, Humphrey Shi, Y. Fu, Yuqian Zhou, Yulun Zhang, Jiahui Yu, Yuchen Fan, Yiqun Mei•Mon Apr 27 2020

A novel Pyramid Attention module for image restoration, which captures long-range feature correspondences from a multi-scale feature pyramid, and is designed to be able to borrow clean signals from their "clean" correspondences at the coarser levels.

101 0

Memory-Efficient Network for Large-scale Video Compressive Sensing

Xin Yuan, Zhengjue Wang, Ziheng Cheng, Bo Chen, Guanliang Liu, Ruiying Lu•Wed Mar 03 2021

This paper develops a memory-efficient network for large-scale video SCI based on multi-group reversible 3D convolutional neural networks and takes one step further to combine demosaicing and SCI reconstruction to directly recover color video from Bayer measurements.

72 0

Projected Distribution Loss for Image Enhancement

Hossein Talebi, P. Milanfar, M. Delbracio•Tue Dec 15 2020

It is demonstrated that aggregating 1D-Wasserstein distances between CNN activations is more reliable than the existing approaches, and it can significantly improve the perceptual performance of enhancement models.

40 0

A Framework for Fast Image Deconvolution With Incomplete Observations

J. Chanussot, M. Simões, L. Almeida, J. Bioucas-Dias•Tue Feb 02 2016

This paper proposes a new deconvolution framework for images with incomplete observations that allows us to work with diagonalized convolution operators, and therefore is very fast, and proposes a specific implementation of this framework, based on the alternating direction method of multipliers (ADMM).

15 0

Adding a benchmark result helps the community track progress.

Demosaicking | State-of-the-Art