In this paper, we formulate the colorization-based coding problem into an optimization problem, i.e., an L₁ minimization problem. In colorization-based coding, the encoder chooses a few representative pixels (RP) for which the chrominance values and the positions are sent to the decoder, whereas in the decoder, the chrominance values for all the pixels are reconstructed by colorization methods. The main issue in colorization-based coding is how to extract the RP well therefore the compression rate and the quality of the reconstructed color image becomes good. By formulating the colorization-based coding into an L₁ minimization problem, it is guaranteed that, given the colorization matrix, the chosen set of RP becomes the optimal set in the sense that it minimizes the error between the original and the reconstructed color image. In other words, for a fixed error value and a given colorization matrix, the chosen set of RP is the smallest set possible. We also propose a method to construct the colorization matrix that colorizes the image in a multiscale manner. This, combined with the proposed RP extraction method, allows us to choose a very small set of RP. It is shown experimentally that the proposed method outperforms conventional colorization-based coding methods as well as the JPEG standard and is comparable with the JPEG2000 compression standard, both in terms of the compression rate and the quality of the reconstructed color image.

Recently, several RGB-White (RGBW) color filter arrays (CFAs) have been proposed, which have extra white (W) pixels in the filter array that are highly sensitive. Due to the high sensitivity, the W pixels have better SNR (Signal to Noise Ratio) characteristics than other color pixels in the filter array, especially, in low light conditions. However, most of the RGBW CFAs are designed so that the acquired RGBW pattern image can be converted into the conventional Bayer pattern image, which is then again converted into the final color image by using conventional demosaicing methods, i.e., color interpolation techniques. In this paper, we propose a new RGBW color filter array based on a totally different color interpolation technique, the colorization algorithm. The colorization algorithm was initially proposed for colorizing a gray image into a color image using a small number of color seeds. Here, we adopt this algorithm as a color interpolation technique, so that the RGBW color filter array can be designed with a very large number of W pixels to make the most of the highly sensitive characteristics of the W channel. The resulting RGBW color filter array has a pattern with a large proportion of W pixels, while the small-numbered RGB pixels are randomly distributed over the array. The colorization algorithm makes it possible to reconstruct the colors from such a small number of RGB values. Due to the large proportion of W pixels, the reconstructed color image has a high SNR value, especially higher than those of conventional CFAs in low light condition. Experimental results show that many important information which are not perceived in color images reconstructed with conventional CFAs are perceived in the images reconstructed with the proposed method.

In this paper, we propose a deep-image-prior-based demosaicing method for a random RGBW color filter array (CFA). The color reconstruction from the random RGBW CFA is performed by the deep image prior network, which uses only the RGBW CFA image as the training data. To our knowledge, this work is a first attempt to reconstruct the color image with a neural network using only a single RGBW CFA in the training. Due to the White pixels in the RGBW CFA, more light is transmitted through the CFA than in the case with the conventional RGB CFA. As the image sensor can detect more light, the signal-to-noise-ratio (SNR) increases and the proposed demosaicing method can reconstruct the color image with a higher visual quality than other existing demosaicking methods, especially in the presence of noise. We propose a loss function that can train the deep image prior (DIP) network to reconstruct the colors from the White pixels as well as from the red, green, and blue pixels in the RGBW CFA. Apart from using the DIP network, no additional complex reconstruction algorithms are required for the demosaicing. The proposed demosaicing method becomes useful in situations when the noise becomes a major problem, for example, in low light conditions. Experimental results show the validity of the proposed method for joint demosaicing and denoising.

A joint demosaicing and denoising task refers to the task of simultaneously reconstructing and denoising a color image from a patterned image obtained by a monochrome image sensor with a color filter array. Recently, inspired by the success of deep learning in many image processing tasks, there has been research to apply convolutional neural networks (CNNs) to the task of joint demosaicing and denoising. However, such CNNs need many training data to be trained, and work well only for patterned images which have the same amount of noise they have been trained on. In this paper, we propose a variational deep image prior network for joint demosaicing and denoising which can be trained on a single patterned image and works for patterned images with different levels of noise. We also propose a new RGB color filter array (CFA) which works better with the proposed network than the conventional Bayer CFA. Mathematical justifications of why the variational deep image prior network suits the task of joint demosaicing and denoising are also given, and experimental results verify the performance of the proposed method.

Over the past decade, deep learning-based computer vision methods have been shown to surpass previous state-of-the-art computer vision techniques in various fields, and have made great progress in various computer vision problems, including object detection, object segmentation, face recognition, etc. Nowadays, major IT companies are adding new deep-learning-based computer technologies to edge devices such as smartphones. However, since the computational cost of deep learning-based models is still high for edge devices, research is being actively carried out to compress deep learning-based models while not sacrificing high performance. Recently, many lightweight architectures have been proposed for deep learning-based models which are based on low-rank approximation. In this paper, we propose an alternating tensor compose-decompose (ATCD) method for the training of low-rank convolutional neural networks. The proposed training method can better train a compressed low-rank deep learning model than the conventional fixed-structure based training method, so that a compressed deep learning model with higher performance can be obtained in the end of the training. As a representative and exemplary model to which the proposed training method can be applied, we propose a rank-1 convolutional neural network (CNN) which has a structure alternatively containing 3-D rank-1 filters and 1-D filters in the training stage and a 1-D structure in the testing stage. After being trained, the 3-D rank-1 filters can be permanently decomposed into 1-D filters to achieve a fast inference in the test time. The reason that the 1-D filters are not being trained directly in 1-D form in the training stage is that the training of the 3-D rank-1 filters is easier due to the better gradient flow, which makes the training possible even in the case when the fixed structured network with fixed consecutive 1-D filters cannot be trained at all. We also show that the same training method can be applied to the well-known MobileNet architecture so that better parameters can be obtained than with the conventional fixed-structure training method. Furthermore, we show that the 1-D filters in a ResNet like structure can also be trained with the proposed method, which shows the fact that the proposed method can be applied to various structures of networks.