Deep patch-wise colorization model for grayscale images

Liang, Xiangguo; Su, Zhuo; Xiao, Yiqi; Luo, Xiaonnan

doi:10.1145/3005358.3005375

Cited by 9 publications

(7 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This algorithm was evaluated with the help of human participants asking them to distinguish between colorized and ground-truth images. In [24], the authors introduced a patch-based colorization model using two different loss functions in a vectorized Convolutional Neural Network framework. During colorization patches are extracted from the image and are colorized independently.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Twin Deep Convolutional Neural Network for Example-Based Image Colorization

Varga

Szirányi

2017

Computer Analysis of Images and Patterns

View full text Add to dashboard Cite

Abstract. This paper deals with the colorization of grayscale images. Recent papers have shown remarkable results on image colorization utilizing various deep architectures. Unlike previous methods, we perform colorization using a deep architecture and a reference image. Our architecture utilizes two parallel Convolutional Neural Networks which have the same structure. One CNN, which uses the reference image, helps the other CNN in color prediction for the input image. On the other hand, the second CNN, which uses the input image, helps to identify the areas which holds essential information about the color scheme of the scene. Comprehensive experiments and qualitative and quantitative evaluations were conducted on the images of SUN database and on other images. Quantitative evaluations are based on Peak Signal-to-Noise Ratio (PSNR) and on Quaternion Structural Similarity (QSSIM).

show abstract

Section: Related Workmentioning

confidence: 99%

“…As pointed out in many papers [20], [23], [24], [26], Euclidean loss function is not an optimal solution because it will result in the so-called averaging problem. Namely, the system will produce grayish sepia tone effects.…”

Section: Our Approachmentioning

confidence: 99%

Twin Deep Convolutional Neural Network for Example-Based Image Colorization

Varga

Szirányi

2017

Computer Analysis of Images and Patterns

View full text Add to dashboard Cite

show abstract

“…This algorithm was evaluated with the help of human participants asking them to distinguish between colorized and ground-truth images. In [16], the authors introduced a patch-based colorization model using two different loss functions in a vectorized Convolutional Neural Network framework. During colorization patches are extracted from the image and colorized independently.…”

Section: Related Workmentioning

confidence: 99%

Automatic Cartoon Colorization Based on Convolutional Neural Network

Varga

Szabó

Szirányi

2017

Proceedings of the 15th International Workshop on Content-Based Multimedia Indexing

View full text Add to dashboard Cite

This paper deals with automatic cartoon colorization. This is a hard issue, since it is an ill-posed problem that usually requires user intervention to achieve high quality. Motivated by the recent successes in natural image colorization based on deep learning techniques, we investigate the colorization problem at the cartoon domain using Convolutional Neural Network. To our best knowledge, no existing papers or research studies address this problem using deep learning techniques. Here we investigate a deep Convolutional Neural Network based automatic color filling method for cartoons.

show abstract

“…AlexNet got 16% of errors in ImageNet call. In the next couple of years, VG 19 [2] with 19 layers and GoogleNet [3] with 22 layers reduced the error rate to a few percent.…”

Section: Introductionmentioning

confidence: 99%

Image Colorization

Mikhalina¹,

Kuz'menko²,

Dergachev³

et al. 2019

GraphiCon'2019 Proceedings. Volume 2

View full text Add to dashboard Cite

The article discusses one of the latest ways to colorize a black and white image using deep learning methods. For colorization, a convolutional neural network with a large number of layers (Deep convolutional) is used, the architecture of which includes a ResNet model. This model was pre-trained on images of the ImageNet dataset. A neural network receives a black and white image and returns a colorized color. Since, due to the characteristics of ResNet, an input multiple of 255 is received, a program was written that, using frames, enlarges the image for the required size. During the operation of the neural network, the CIE Lab color model is used, which allows to separate the black and white component of the image from the color. For training the neural network, the Place 365 dataset was used, containing 365 different classes, such as animals, landscape elements, people, and so on. The training was carried out on the Nvidia GTX 1080 video card. The result was a trained neural network capable of colorizing images of any size and format. As example we had a speed of 0.08 seconds and an image of 256 by 256 pixels in size. In connection with the concept of the dataset used for training, the resulting model is focused on the recognition of natural landscapes and urban areas.

show abstract

Deep patch-wise colorization model for grayscale images

Cited by 9 publications

References 9 publications

Twin Deep Convolutional Neural Network for Example-Based Image Colorization

Twin Deep Convolutional Neural Network for Example-Based Image Colorization

Automatic Cartoon Colorization Based on Convolutional Neural Network

Image Colorization

Contact Info

Product

Resources

About