Sufficient Image Appearance Transfer Combining Color and Texture

Song, Zhichao; Liu, Shiguang

doi:10.1109/tmm.2016.2631123

Cited by 38 publications

(10 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Xie et al [31] designed a new color transfer model with an adaptive second-order total generalized variation (TGV) regularizer. Song et al [32] proposes a new image appearance transfer method combining both color and texture features, which can obtain sufficient appearance transfer results. Wang et al [7] presented a ℒ0 gradientpreserving color transfer method which forced the consistence of pixel gradients of the color region in the resulting image with that in the source image and emphasized the similarities between source image pixel colors.…”

Section: Related Workmentioning

confidence: 99%

Color Transfer With Salient Features Mapping via Attention Maps Between Images

Ren

2020

IEEE Access

View full text Add to dashboard Cite

Color transfer is a useful image editing technology that transfers the color style of a reference image to a source image. In this paper, a novel automatic perception color transfer method based on salient features mapping was proposed. Firstly, the saliency maps of the reference image and source image are built to predict the human visual attention regions. Secondly, the gradient map is calculated by convolving the image pair with Sobel filter. Thirdly, the saliency map and gradient map are combined to produce a weighted attention map. Fourthly, by thresholding the attention map the reference image and the source image are segmented into regions of salient and non-salient pixels, and mean and standard deviation of these two regions are calculated in the three channels of the YUV space, respectively. Finally, on the salient and non-salient pixels an execution similar to Reinhard's is performed, and the two results are combined to generate the final output. The experiments result show the superiority of our method by its pleasant natural appearance with color similarity and image details preservation, high time efficiency and easy implementation.

show abstract

Section: Related Workmentioning

confidence: 99%

Color Transfer With Salient Features Mapping via Attention Maps Between Images

Ren

2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…A unified Bayesian framework is utilized in the background-foreground fusion stage. Song et al [43] have propose a new method for image appearance transfer that combines color and texture features. To do this, they imlemented feature detection and matching between source and reference images.…”

Section: Related Workmentioning

confidence: 99%

Spatiotemporal road scene reconstruction using superpixel-based Markov random field

Liu

Zhu

et al. 2020

Information Sciences

View full text Add to dashboard Cite

“…The automatic palette extraction approach, which preserves inherent color characteristics of the source image, was able to create more natural results than previous works. Color transfer studies are being studied through various methods, such as [26,27,28].…”

Section: Related Workmentioning

confidence: 99%

Emotion-Inspired Painterly Rendering

2020

View full text Add to dashboard Cite

When painters draw, they do not draw what they see; they reflect their emotions through specific forms of artistic expression. Through this empathy, humans derive aesthetic satisfaction. Psychological studies on art and emotions have been extensively conducted since the 20th century, and it has been found that artistic activities such as painting and writing have a positive effect on human emotions. However, it is difficult for a non-professional painter to express human emotions in a picture using artistic elements. The aim of this study was to propose a "user emotion-inspired painterly rendering process" to help non-professionals reflect their emotions through painting. To accomplish this aim, a painter-rendering system that automatically creates digital paintings with parameterized painting features was used. We analyzed the correlation between human emotions and the rendering parameters affecting the painting style through a user study, and we estimated the rendering parameter values for specific emotions. The results showed that colors and emotions were closely linked, and color scheme was an influential factor in the paintings. Furthermore, we developed a recoloring algorithm based on Kobayashi's three color systems classified as human emotions, and we created paintings that better reflect specific emotions. The proposed algorithm was validated through a user satisfaction survey. Hence, the proposed system can improve a user's understanding of painting and create paintings that reflect specific emotions.

show abstract

Sufficient Image Appearance Transfer Combining Color and Texture

Cited by 38 publications

References 30 publications

Color Transfer With Salient Features Mapping via Attention Maps Between Images

Color Transfer With Salient Features Mapping via Attention Maps Between Images

Spatiotemporal road scene reconstruction using superpixel-based Markov random field

Emotion-Inspired Painterly Rendering

Contact Info

Product

Resources

About