SCCGAN: Style and Characters Inpainting Based on CGAN

Liu, Ruijun; Xiangshang, Wang; Lu, Huimin; Wu, Zhaohui; Fan, Qiang; Li, Shanxi; Jin, Xin

doi:10.1007/s11036-020-01717-x

Cited by 75 publications

(40 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With the development of science and technology, the means and forms of animation are becoming more and more diversified. In the field of animation, almost all the forms of plane painting and the modeling of three-dimensional idols can be seen, such as simple and clear lines [14], fresh watercolor, gouache, color lead, ink with strong Chinese style, print and decorative painting with simple but warm colors, oil painting, ink-jet painting, computer painting, clay sculpture, puppet, paper-cut, bamboo, and other folk crafts [15]. The digital revolution of animation makes the theme of the story be told more plastic and also makes the animation director expand his knowledge field and quality ability, and the way of telling the story becomes diverse and innovative to cater to the audience's freshness; in the use of lens, in the threedimensional world, any way of lens movement becomes possible [16][17][18].…”

Section: The Extension Of Animation Categorymentioning

confidence: 99%

[Retracted] Application of Photoshop Graphics and Image Processing in the Field of Animation

2021

Journal of Sensors

View full text Add to dashboard Cite

With the rapid development of digital art and machine science and technology, the production form of modern animation tends to be diversified, and with the important role of animation color in the animation film foil and rendering, more and more attention was paid by the animation design industry. Computer graphic technology is a new type of artistic creation method, and its birth and development are closely related to computer technology. The purpose of this paper is to make some analysis and induction from the perspective of science and technology and culture and to explore the application of Photoshop graphics and image processing technology in the field of animation. First, the definition of “animation” and the extension of the animation category are introduced. Then, the main functions of Photoshop image processing technology are described in detail. According to the research content, this paper designs a self-made experimental short film “future city.” After the simulation of experimental animation film and the setting and positioning of the experimental scene, Photoshop software was used to show the animation scene. The experimental results show that the color changes in the short film “future city.” After the saturation of sunny scenery is reduced by 3 points and the brightness is reduced by 20 points and the filter, mode change, and color adjustment are carried out, a complete rainy scenery can be obtained. The self-made experimental short film has guiding significance for the creation and practice.

show abstract

Section: The Extension Of Animation Categorymentioning

confidence: 99%

[Retracted] Application of Photoshop Graphics and Image Processing in the Field of Animation

2021

Journal of Sensors

View full text Add to dashboard Cite

show abstract

“…Lv et al proposed a deep-learning-based fine-grained visual computation [ 11 ]. Liu et al have investigated the Style and Characters Inpainting Based on CGAN [ 12 ]. Road detection, stereo reconstruction, light current visual measurement, 3D object detection, and 3D tracking are the principal functions of this dataset ( http://www.cvlibs.net/datasets/kitti/ ).…”

Section: Datasets and Evaluation Metricsmentioning

confidence: 99%

“…This method is for radiologists to evaluate the results of DL segmentation, make changes, and frequently add more tutorials to update the model. As a result, they speed up the algorithm's development cycle [ 12 ]. As recent findings show, before choosing to use chest CT, a significant number of imaging studies need to be checked for patient diagnosis or patient screening.…”

Section: Introductionmentioning

confidence: 99%

The Progress of Medical Image Semantic Segmentation Methods for Application in COVID‐19 Detection

Valizadeh

Shariatee

2021

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Image medical semantic segmentation has been employed in various areas, including medical imaging, computer vision, and intelligent transportation. In this study, the method of semantic segmenting images is split into two sections: the method of the deep neural network and previous traditional method. The traditional method and the published dataset for segmentation are reviewed in the first step. The presented aspects, including all-convolution network, sampling methods, FCN connector with CRF methods, extended convolutional neural network methods, improvements in network structure, pyramid methods, multistage and multifeature methods, supervised methods, semiregulatory methods, and nonregulatory methods, are then thoroughly explored in current methods based on the deep neural network. Finally, a general conclusion on the use of developed advances based on deep neural network concepts in semantic segmentation is presented.

show abstract

“…Compared with traditional hand-designed features such as Haar, local binary patterns (LBP), histogram of oriented gradient (HOG) and scale-invariant feature transform (SIFT), deep convolutional neural network (DCNN) has richer learning features and stronger expressive ability [19]. DL has been widely used in various computer vision tasks [20][21][22]. Under the supervision and training of a large number of labelled training sets, the static image classification and target detection based on the DCNNs have achieved remarkable results.…”

Section: Related Workmentioning

confidence: 99%

Image semantic segmentation method based on GAN network and ENet model

Li¹

2021

J. eng.

View full text Add to dashboard Cite

Currently, image semantic segmentation has problems such as low accuracy and long running time. This paper proposes an image semantic segmentation method based on generative adversarial network and ENet model combined with deep neural network. This method first improves the network model of generative adversarial network. Ensure the high resolution of the generated image and achieve high similarity with the real image. While ensuring the high accuracy of image semantic segmentation, it effectively improves the real-time performance of network processing. The proposed method is verified based on public data sets. The experimental results show that the segmentation accuracy of this method can reach more than 93%, and the simulation running time is less than 0.171 s, which shows good high accuracy and high real-time performance. A feasible strategy is proposed for the further productization of semantic segmentation.

show abstract

SCCGAN: Style and Characters Inpainting Based on CGAN

Cited by 75 publications

References 31 publications

[Retracted] Application of Photoshop Graphics and Image Processing in the Field of Animation

[Retracted] Application of Photoshop Graphics and Image Processing in the Field of Animation

The Progress of Medical Image Semantic Segmentation Methods for Application in COVID‐19 Detection

Image semantic segmentation method based on GAN network and ENet model

Contact Info

Product

Resources

About