Depth-aware image vectorization and editing

Lu, Shufang; Jiang, Wenhong; Ding, Xuefeng; Kaplan, Craig S.; Jin, Xiaogang; Gao, Fei; Chen, Jiazhou

doi:10.1007/s00371-019-01671-0

Cited by 12 publications

(11 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…But it still results in too many primitives, prohibiting the vectorized images from further editing. Lu et al [21] proposed a vectorization method for RGB-D images, which extracts DCs from both color space and depth map. Their method works only for indoor scene images, due to strict working condition of the current RGB-D cameras.…”

Section: Related Workmentioning

confidence: 99%

Hierarchical Vectorization for Portrait Images

Fu¹,

Liu²,

Hou³

et al. 2022

Preprint

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

Section: Related Workmentioning

confidence: 99%

Hierarchical Vectorization for Portrait Images

Fu¹,

Liu²,

Hou³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…It is intuitive for users because it supports traditional freehand drawing techniques, and edges/curves are viewed as natural primitives for encoding and editing images [11]. Subsequent works on diffusion curves mainly focus on the rendering acceleration [4], [5], [12], image quality improvement [3], [13], [14], color diffusion control [15]- [19], new forms of diffusion curves extension [6], [20], [21], and its applications [22], [23].…”

Section: Related Workmentioning

confidence: 99%

“…Xie et al [2] developed a hierarchical diffusion curves representation to make their results more editable, but it is limited to generating visual abstraction rather than editing the shape of DCI. Lu et al [14] proposed a diffusion-curve-based image vectorization framework for RGBD images. It supports the editing of objects that are segmented by using both color and depth information.…”

Section: Related Workmentioning

confidence: 99%

Shape Manipulation of Diffusion Curves Images

Ding

Gao

et al. 2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

Diffusion curves image (DCI) is a kind of vector graphics with its geometric primitives defined by a set of Bézier curves. As one of the vector graphics, editability is an important property for diffusion curves. However, most of the current DCI shape manipulation methods are typically limited to single curve. It is tedious for users to edit the shape of DCI by deforming each curve individually, especially with the increasing number of curves. In addition, the image contents cannot well preserved because there is no constraints among curves. We present an efficient and flexible DCI manipulation method by combining global and local deformations. The overall shape is easily changed by our global manipulation tool with a few user interactions, while the local manipulation tool is used to modify details. These two tools can be combined to obtain desired effects. In both cases, the constraints during deformation preserve the quality of the editing results. Our experimental results demonstrate that the proposed method provides more convenient control for DCI shape editing than existing techniques based on diffusion curves. INDEX TERMS Shape manipulation, vector graphics, diffusion curves images.

show abstract

“…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]. In general, there are three geometric base primitives for transforming a bitmap into a vector image, which are diffusion curve, gradient mesh, and triangles.…”

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

Depth-aware image vectorization and editing

Cited by 12 publications

References 37 publications

Hierarchical Vectorization for Portrait Images

Hierarchical Vectorization for Portrait Images

Shape Manipulation of Diffusion Curves 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