Colorization Scheme Research Articles

A fully-automatic image colorization scheme using improved CycleGAN with skip connections

Image colorization is the process of assigning different RGB values to each pixel of a given grayscale image to obtain the corresponding colorized image. In this work, we propose a new automatic image colorization method based on the modified cycle-consistent generative adversarial network (CycleGAN). This method can generate a natural color image with only one given gray image without reference image or manual interaction. In the proposed method, we first modify the original network structure by combining a u-shaped network with a skip connection to improve the ability of feature representation in image colorization. Meanwhile, we design a compounded loss function to measure the errors between the ground-truth image and the predicted result to improve the authenticity and naturalness of the colorized image; further, we also add the detail loss function to ensure that the details of the generated color and grayscale images are substantially similar. Finally, the performance of the proposed model is verified on different datasets. Experiments show that our method can generate more realistic color images when compared to other methods.

Grey is the new RGB: How good is GAN-based image colorization for image compression?

GAN-based image colorization techniques are capable of producing highly realistic color in real-time. Subjective assessment of these approaches has demonstrated that humans are unable to differentiate between a true RGB image and a colorized image. In this work, we evaluate the fidelity of such colorization and for the first time analyze the GAN-based image colorization scheme in the context of image compression. Our analysis shows that the palette (set of colors) recommended by the GAN-based framework is very limited even for highly realistic interactive colorization. We propose two novel methods of automatic palette generation that allows for the GAN-based framework to be useful for image compression. We demonstrate that provided true colors at a few pixel locations, GAN-based approach results in good spread of color to other image regions. Subjective analysis on a number of public datasets shows that the current system has low fidelity but performs better than JPEG at low data rate regimes.

From Coarse to Fine (FC2F): A New Scheme of Colorizing Thermal Infrared Images

Colorization of the thermal infrared image is an unsolved problem because usually there is no one-to-one relationship between an object's color and its temperature. In this paper, we propose a new colorization scheme to address this problem. We first create a coarse colorization image that maintains cross-correlation between its RGB channels. Then the matrix of shift, rotation, and scaling between the coarse colorization image and a source natural color image is constructed. Finally, the transformations act on the coarse colorization image to obtain the resultant image, which has the appearance of the source image. Experiments demonstrate the effectiveness of the new scheme and show its superiority to other state-of-the-art methods. The new scheme can be easily extended to the colorization of low illumination images and near-infrared images.

User tailored colorization using automatic scribbles and hierarchical features

Fully automatic image colorization is extensively developed using a large number of examples. However, this kind of methods need further detailed revision if users require fine colorization for delicate objects. This paper proposes a novel scribble-based colorization scheme which automatically generates scribbles and propagates color information from representative pixels within homogeneous superpixels. The scribbles are placed in the regions with minimal entropy to ensure color propagation from representative pixels with high confidence. To avoid color bleeding and under colorization, colors are propagated under a robust similarity metric using a set of hierarchical features, where the low level features consist of quaternion Gabor phases and the high level features are extracted using VGG-19 pre-trained deep model. Experimental results on open dataset demonstrate that the proposed colorization scheme can achieve more consistent results with the users' purposes.

A Data-Driven Approach for Furniture and Indoor Scene Colorization.

We present a data-driven approach that colorizes 3D furniture models and indoor scenes by leveraging indoor images on the internet. Our approach is able to colorize the furniture automatically according to an example image. The core is to learn image-guided mesh segmentation to segment the model into different parts according to the image object. Given an indoor scene, the system supports colorization-by-example, and has the ability to recommend the colorization scheme that is consistent with a user-desired color theme. The latter is realized by formulating the problem as a Markov random field model that imposes user input as an additional constraint. Our system is able to imitate the colorization results for those scenes containing the same type of objects, but with spatially varied patterns. We contribute to the community a hierarchically organized image-model database with correspondences between each image and the corresponding model at the part-level. Our experiments and a user study show that our system produces perceptually convincing results comparable to those generated by interior designers.

Perceptually‐based Color Assignment

AbstractColor assignment is a complex task of incorporating and balancing area configuration, color harmony, and user's intent. In this paper, we present a novel method for automatic color assignment based on theories of color perception. We define color assignment as an optimization problem with respect to the color relationships as well as the spatial configuration of input segments. We also suggest possible constraints that are suitable for task‐specific purposes and for enhancing visual appeal. Our colorization scheme is useful in many applications such as infographics, computer‐aided design, and visual presentation. The user study shows that our method generates perceptually pleasing results over a variety of data sets.

Application of the Extended Distance Transformation in digital image colorization

In this paper we present a novel colorization scheme that takes advantage of the modified morphological distance transform to propagate the color, scribbled by a user on the grayscale image. First, based on the scribbled image, the topological distance values are computed for each image pixel, describing its distance to the inserted color markers. These values are then complemented with the structural information and luminance changes derived from the original grayscale image. The distances are then used along with gradient based features to reproduce original image structures while propagating the new colors obtained during the additive color blending process. Extensive experiments performed on various kinds of natural images demonstrated the effectiveness of the proposed colorization method. They also showed that the main advantage of the presented algorithm is its computational speed and ability to produce visually pleasing colorization results promptly after providing the color information.

Processing of interlaced images in 4–10 MeV dual energy customs system for material recognition

The aim of this article is to demonstrate the practical value of radioscopic differentiation of materials in the 1--10 MeV energy range to the work of customs services. The proposed method for achieving singling out and identifying four basic groups of materials according to an atomic number is complex. Atomic numbers are identified using high- and low-energy profiles obtained through the irradiation of materials on an alternate pulse-by-pulse basis. This is done using a bremsstrahlung beam with $8\text{ }\mathrm{MeV}/4\text{ }\mathrm{MeV}$ dual boundary energies and by using scintillating crystals coupled with silicon photodiodes as detecting elements. An image segmentation technique is then used to discern the distribution of an atomic number on any given image. The color visualization of integral absorption and a material's atomic composition is carried out according to the intensity hue saturation (IHS) colorization scheme. The experiments were carried out on a full-scale prototype of an 8 MeV customs inspection system developed by the Efremov Research Institute.