DeepDemosaicking: Adaptive Image Demosaicking via Multiple Deep Fully Convolutional Networks

Tan, Daniel Stanley; Chen, Wei-Yang; Hua, Kai-Lung

doi:10.1109/tip.2018.2803341

Cited by 84 publications

(46 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For a complete survey of recent approaches, we refer to [1]. One of the main drawbacks of the currently introduced methods that deal with the demosaicking problem, is that they assume a specific Bayer pattern [1], [2], [3], [4], [5], [6], [7]. This is a rather strong assumption and limits their applicability since there are many cameras available in the market that employ different Color Filter Array (CFA) patterns, for example, Fuji sensors.…”

Section: Introductionmentioning

confidence: 99%

“…During recent years, research is directed towards learning based approaches, although a common problem with the design of learning based demosaicking algorithms is the lack of ground-truth images. In many approaches such as those in [9], [10], [7] the authors used already processed images as references that are simulated mosaicked again, i.e. they apply a mosaick mask on the already demosaicked images, therefore obtaining non-realistic pairs for tuning trainable methods.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Iterative Joint Image Demosaicking and Denoising Using a Residual Denoising Network

Kokkinos

Lefkimmiatis

2019

IEEE Trans. on Image Process.

103

View full text Add to dashboard Cite

Modern digital cameras rely on the sequential execution of separate image processing steps to produce realistic images. The first two steps are usually related to denoising and demosaicking where the former aims to reduce noise from the sensor and the latter converts a series of light intensity readings to color images. Modern approaches try to jointly solve these problems, i.e. joint denoising-demosaicking which is an inherently ill-posed problem given that two-thirds of the intensity information is missing and the rest are perturbed by noise. While there are several machine learning systems that have been recently introduced to solve this problem, the majority of them relies on generic network architectures which do not explicitly take into account the physical image model. In this work we propose a novel algorithm which is inspired by powerful classical image regularization methods, large-scale optimization, and deep learning techniques. Consequently, our derived iterative optimization algorithm, which involves a trainable denoising network, has a transparent and clear interpretation compared to other black-box data driven approaches. Our extensive experimentation line demonstrates that our proposed method outperforms any previous approaches for both noisy and noisefree data across many different datasets. This improvement in reconstruction quality is attributed to the rigorous derivation of an iterative solution and the principled way we design our denoising network architecture, which as a result requires fewer trainable parameters than the current state-of-the-art solution and furthermore can be efficiently trained by using a significantly smaller number of training data than existing deep demosaicking networks.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Iterative Joint Image Demosaicking and Denoising Using a Residual Denoising Network

Kokkinos

Lefkimmiatis

2019

IEEE Trans. on Image Process.

103

View full text Add to dashboard Cite

show abstract

“…In particular, Convolutional Neural Network (CNN) plays an essential role in many signal processing fields. Many CNN-based methods have been proposed in image demosaicking [1]- [6] and they obtain better performance than conventional demosaicking algorithms. For example, Tan et.al.…”

Section: Introductionmentioning

confidence: 99%

Multi-Stage Dense CNN Demosaicking With Downsampling and Re-Indexing Structure

Yamaguchi

Ikehara

2020

IEEE Access

View full text Add to dashboard Cite

Multi-stage CNN is composed of several networks and loss functions. Compared to a normal single-stage CNN, a multi-stage CNN can control the processing in each network. In image demosaicking, it is utilized to follow the flow of conventional non-CNN demosaicking algorithms. This paper proposes a 4-stage CNN demosaicking method. The first stage obtains a pre-estimated full color image from an input Bayer image instead of non-CNN pre-processing. The second stage processes the color planes independently while the third stage processes the combination for two colors. The final stage obtains the full-color outputs from all outputs of the former stages. To achieve better performance, the proposed method introduces dense structures for both inside and outside of every network. Another contribution is dealing with the discontinuity between a pixel and its neighboring pixels in Bayer images by a downsampling and re-indexing structure for feature maps. These contributions lead to higher accuracy and prevent false colors. Some results through demosaicking experiments show that the proposed method can achieve better quality images with less false colors and better PSNR than state-of-the-art CNN demosaicking methods.

show abstract

“…Quality Enhancement Due to the existence of cross-channel correlation, many works refine each channel by other channels' reconstruction alternatively and iteratively (e.g., [26] [36]). Some of these works have achieved the top demosaicing accuracy on benchmarks yet is faster than many classical methods (e.g., [34]).…”

Section: Introductionmentioning

confidence: 99%

“…Some of these works have achieved the top demosaicing accuracy on benchmarks yet is faster than many classical methods (e.g., [34]). An implicit cost for CNN is the non-trivial memory required to store the trained model (e.g., [34], [36]) .…”

Section: Introductionmentioning

confidence: 99%

Low Cost Edge Sensing for High Quality Demosaicking

Yan

Ouyang

Zuo

et al. 2019

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

Digital cameras that use Color Filter Arrays (CFA) entail a demosaicking procedure to form full RGB images. As today's camera users generally require images to be viewed instantly, demosaicking algorithms for real applications must be fast. Moreover, the associated cost should be lower than the cost saved by using CFA. For this purpose, we revisit the classical Hamilton-Adams (HA) algorithm, which outperforms many sophisticated techniques in both speed and accuracy. Based on a close look at HA's strength and weakness, we design a very low cost edge sensing scheme. Briefly, it guides demosaicking by a logistic functional of the difference between directional variations. We extensively compare our algorithm with 28 demosaicking algorithms by running their open source codes on benchmark datasets. Compared to methods of similar computational cost, our method achieves substantially higher accuracy; Whereas compared to methods of similar accuracy, our method has significantly lower cost. Moreover, on test images of currently popular resolution, the quality of our algorithm is comparable to top performers, whereas its speed is tens of times faster.

show abstract

DeepDemosaicking: Adaptive Image Demosaicking via Multiple Deep Fully Convolutional Networks

Cited by 84 publications

References 48 publications

Iterative Joint Image Demosaicking and Denoising Using a Residual Denoising Network

Iterative Joint Image Demosaicking and Denoising Using a Residual Denoising Network

Multi-Stage Dense CNN Demosaicking With Downsampling and Re-Indexing Structure

Low Cost Edge Sensing for High Quality Demosaicking

Contact Info

Product

Resources

About