Vectorization Based Color Transfer for Portrait Images

Fu, Qian; He, Ying; Hou, Fei; Zhang, Jie; Zeng, Anxiang; Liu, Yong-Jin

doi:10.1016/j.cad.2019.05.005

Cited by 12 publications

(26 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They employed a simple color transfer method with DFT and variance features to obtain the preliminary colorization results with incoherent colors. Fu et al [37] presented a method for transferring colors between portrait images. They used a trained neural network to extract facial masks and encoded the low-frequency colors by vectoring the image pair with the sparse diffusion curves.…”

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

“…To make a fair comparison with intrinsic image based methods, we calculate IS-FLIP and FLIP for the facial regions, since the existing intrinsic image decomposition can only process the face regions. For vectorization, our method can obtain similar accuracy of the conventional PVG vectorization method [14]. For color transfer, our method yields results with the highest quality.…”

Section: Resultsmentioning

confidence: 76%

“…The raster-image based methods apply OMT to the original images, the intrinsic images, and the L 1 smoothed images. The vectorization based methods are the 2-level PVG [14], and the intrinsic image-based PVG which vectorizes each decomposed layer using [14]. Table 2 reports the mean and variance of the IS-FLIP-ct and FLIP metrics on 500 representative images (No.…”

Section: Resultsmentioning

confidence: 99%

“…Portrait image & video editing has been studied extensively, resulting in a large body of literature. The works that are most relevant to ours are lighting transfer using optimal mass transport [30] and deep neural networks [38,41], vectorization guided color transfer [14], style transfer through deep image analogy [19], and deep learning based color transfer [1], geometry editing [11], expression synthesis [22], contrast transfer [29] and style transfer [28]. The neural model based methods have demonstrated promising performance in many tasks.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Hierarchical Vectorization for Portrait Images

Fu¹,

Liu²,

Hou³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

The explosive growth of social media makes portrait editing and retouching in high demand. Though portraits are commonly captured and stored as raster images, editing raster images is non-trivial and often requires the user to be highly skilled. Aiming at developing intuitive and easy-to-use portrait editing tools, we propose a novel vectorization method that can automatically convert raster images into a 3-tier hierarchical representation. The base layer consists of a set of sparse diffusion curves (DC) which characterize salient geometric features and low-frequency colors and provide means for semantic color transfer and facial expression editing. The middle level encodes specular highlights and shadows to large and editable Poisson regions (PR) and allows the user to directly adjust illumination via tuning the strength and/or changing shape of PR. The top level contains two types of pixel-sized PRs for highfrequency residuals and fine details such as pimples and pigmentation. We also train a deep generative model that can produce high-frequency residuals automatically. Thanks to the meaningful organization of vector primitives, editing portraits becomes easy and intuitive. In particular, our method supports color transfer, facial expression editing, highlight and shadow editing and automatic retouching. To quantitatively evaluate the results, we extend the commonly used FLIP metric (which measures color and feature differences between two images) by considering illumination. The new metric, called illumination-sensitive FLIP or IS-FLIP, can effectively capture the salient changes in color transfer results, and is more consistent with human perception than FLIP and other quality measures on portrait images. We evaluate our method on the FFHQR dataset and show that our method is effective for common portrait editing tasks, such as retouching, light editing, color transfer and expression editing. We will make the code and trained models publicly available.

show abstract

“…e vector image is represented by geometric base primitives. It has wide applications such as [5] and may apply to some other domains like image captioning [6][7][8]. Recently, some new methods for image vectorization are proposed [9][10][11][12].…”

Section: Related Workmentioning

confidence: 99%

A Novel Approach to Transform Bitmap to Vector Image for Data Reliable Visualization considering the Image Triangulation and Color Selection

Han

Chi

et al. 2020

Security and Communication Networks

View full text Add to dashboard Cite

Vector image is a type of image composed of many geometric primitives. Compared with bitmaps, vector images have the ability to save memory as well as to enlarge without distortion. Meanwhile, it has been commonly adopted in data visualization (image data) because it can be scaled to multiple sizes to fit different scenes. For instance, it can be applied for the illustrations in newspapers and magazines, the logo on the web, the background for poster, the design of text, and traffic signs. However, transforming a bitmap to vector image is still a challenging problem because of the complicated content of a bitmap, which tends to consist of more than just simple geometry. Aiming at this issue, there is a new approach proposed to transform from bitmaps to vector images, which is based on triangle units and consists of three steps. In detail, firstly, there is an initial mesh constructed for one image in pixel level after detecting features. Then, the initial mesh will be simplified by collapsing two vertices as the initial mesh is too dense to represent one image. Specifically, there are two main parts in this step, which are collapse conditions and collapse influences. In the step of collapsing, issues such as overlap and sharp triangles can be conquered by a sort-edge method (which will be illustrated specifically later). The final step is to select one color for each triangle, since it is helpful to save the memory and speed up the process of this method. In addition, one color will represent one triangle; hence, in the final step, the four-triangle sample method will be applied in order to prevent a vector image from generating too large color discontinuity. Once the pretest proceeds without mistake, the method above is able to work for the general bitmaps. Note that our method can be applied to information security and privacy, since one image can be encoded to some triangles and colors.

show abstract

Vectorization Based Color Transfer for Portrait Images

Cited by 12 publications

References 34 publications

Color Transfer With Salient Features Mapping via Attention Maps Between Images

Color Transfer With Salient Features Mapping via Attention Maps Between Images

Hierarchical Vectorization for Portrait Images

A Novel Approach to Transform Bitmap to Vector Image for Data Reliable Visualization considering the Image Triangulation and Color Selection

Contact Info

Product

Resources

About