scholarly journals Rapid Local Image Style Transfer Method Based on Residual Convolutional Neural Network

2021 ◽  
Vol 33 (4) ◽  
pp. 1343
Author(s):  
Liming Huang ◽  
Ping Wang ◽  
Cheng-Fu Yang ◽  
Hsien-Wei Tseng
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Style Transfer ◽  
Transfer Method ◽  
Local Image

The contour image style-transfer-based convolutional neural network

2019 ◽  
Author(s):  
Nan Deng ◽  
Jing Li ◽  
Xingce Wang ◽  
Zhongke Wu ◽  
yan Fu ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Style Transfer

scholarly journals Depth-Aware Arbitrary Style Transfer Using Instance Normalization

2020 ◽  
pp. paper2-1-paper2-11
Author(s):  
Victor Kitov ◽  
Konstantin Kozlovtsev ◽  
Margarita Mishustina
Keyword(s):  
Neural Network ◽  
Qualitative Analysis ◽  
Loss Function ◽  
Human Perception ◽  
Depth Map ◽  
Evaluation Study ◽  
User Evaluation ◽  
Style Transfer ◽  
Separate Model ◽  
Transfer Method

Style transfer is the process of rendering one image with some content in the style of another image, representing the style. Recent studies of Liu et al. (2017) show that traditional style transfer methods of Gatys et al. (2016) and Johnson et al.(2016) fail to reproduce the depth of the content image, which is critical for human perception. They suggest to preserve the depth map by additional regularizer in the optimized loss function, forcing preservation of the depth map. However these traditional methods are either computationally inefficient or require training a separate neural network for each style. AdaIN method of Huang et al. (2017) allows efficient transferring of arbitrary style without training a separate model but is not able to reproduce the depth map of the content image. We propose an extension to this method, allowing depth map preservation by applying variable stylization strength. Qualitative analysis and results of user evaluation study indicate that the proposed method provides better stylizations, compared to the original AdaIN style transfer method.

scholarly journals An Image Style Transfer Network Using Multilevel Noise Encoding and Its Application in Coverless Steganography

Symmetry ◽  
2019 ◽  
Vol 11 (9) ◽  
pp. 1152
Author(s):  
Shanqing Zhang ◽  
Shengqi Su ◽  
Li Li ◽  
Qili Zhou ◽  
Jianfeng Lu ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Color Image ◽  
Image Data ◽  
Cover Image ◽  
Stego Image ◽  
Style Transfer ◽  
Secret Information ◽  
Residual Learning ◽  
Short Period

Most of the existing image steganographic approaches embed the secret information imperceptibly into a cover image by slightly modifying its content. However, the modification traces will cause some distortion in the stego-image, especially when embedding color image data that usually contain thousands of bits, which makes successful steganalysis possible. A coverless steganographic approach without any modification for transmitting secret color image is proposed. We propose a diversity image style transfer network using multilevel noise encoding. The network consists of a generator and a loss network. A multilevel noise to encode matching the subsequent convolutional neural network scale is used in the generator. The diversity loss is increased in the loss network so that the network can generate diverse image style transfer results. Residual learning is introduced so that the training speed of network is significantly improved. Experiments show that the network can generate stable results with uniform texture distribution in a short period of time. These image style transfer results can be integrated into our coverless steganography scheme. The performance of our steganography scheme is good in steganographic capacity, anti-steganalysis, security, and robustness.

Controlling Stroke Size in Fast Style Transfer with Recurrent Convolutional Neural Network

2018 ◽  
Vol 37 (7) ◽  
pp. 97-107 ◽  
Author(s):  
Lingchen Yang ◽  
Lumin Yang ◽  
Mingbo Zhao ◽  
Youyi Zheng
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Style Transfer

scholarly journals Convolutional Neural Network Style Transfer Towards Chinese Paintings

IEEE Access ◽  
2019 ◽  
Vol 7 ◽  
pp. 163719-163728
Author(s):  
Jiachuan Sheng ◽  
Caifeng Song ◽  
Jun Wang ◽  
Yahong Han
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Style Transfer

A Study on the Convolutional Neural Algorithm of Image Style Transfer

2019 ◽  
Vol 33 (05) ◽  
pp. 1954020 ◽  
Author(s):  
Fu Wen Yang ◽  
Hwei Jen Lin ◽  
Shwu-Huey Yen ◽  
Chun-Hui Wang
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Convolutional Neural Network ◽  
Computational Efficiency ◽  
Back Propagation ◽  
Deep Convolutional Neural Networks ◽  
Propagation Process ◽  
Energy Functions ◽  
Style Transfer ◽  
Artistic Style

Recently, deep convolutional neural networks have resulted in noticeable improvements in image classification and have been used to transfer artistic style of images. Gatys et al. proposed the use of a learned Convolutional Neural Network (CNN) architecture VGG to transfer image style, but problems occur during the back propagation process because there is a heavy computational load. This paper solves these problems, including the simplification of the computation of chains of derivatives, accelerating the computation of adjustments, and efficiently choosing weights for different energy functions. The experimental results show that the proposed solutions improve the computational efficiency and render the adjustment of weights for energy functions easier.

Sign in / Sign up

Export Citation Format

Share Document