Adaptive image vectorisation and brushing using mesh colours

Hettinga, Gerben J.; Echevarria, Jose; Kosinka, Jiří

doi:10.1016/j.cag.2022.05.004

Cited by 5 publications

(5 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For places where the color fitting error exceeds a threshold, new vertices are added, and a constrained Delaunay triangulation is further applied for refinement. More recently, Hettinga et al [51] fit cubic Bézier triangles to an input image, and mapped textures as mesh colors through an optimization process. Later, they extended the vectorization framework to enhance user control and feature extraction [54].…”

Section: Triangular Meshesmentioning

confidence: 99%

See 1 more Smart Citation

A Survey of Smooth Vector Graphics: Recent Advances in Repr esentation, Creation, Rasterization, and Image Vectorization

Tian

Günther

2024

IEEE Trans. Visual. Comput. Graphics

View full text Add to dashboard Cite

The field of smooth vector graphics explores the representation, creation, rasterization, and automatic generation of light-weight image representations, frequently used for scalable image content. Over the past decades, several conceptual approaches on the representation of images with smooth gradients have emerged that each led to separate research threads, including the popular gradient meshes and diffusion curves. As the computational models matured, the mathematical descriptions diverged and papers started to focus more narrowly on subproblems, such as on the representation and creation of vector graphics, or the automatic vectorization from raster images. Most of the work concentrated on a specific mathematical model only. With this survey, we describe the established computational models in a consistent notation to spur further knowledge transfer, leveraging the recent advances in each field. We therefore categorize vector graphics papers from the last decades based on their underlying mathematical representations as well as on their contribution to the vector graphics content creation pipeline, comprising representation, creation, rasterization, and automatic image vectorization. This survey is meant as an entry point for both artists and researchers. We conclude this survey with an outlook on promising research directions and challenges to overcome in the future.

show abstract

Section: Triangular Meshesmentioning

confidence: 99%

“…More recently, Hettinga et al [51] fit cubic Bézier triangles to an input image, and mapped textures as mesh colors through an optimization process. Later, they extended the vectorization framework to enhance user control and feature extraction [54].…”

Section: Triangular Meshesmentioning

confidence: 99%

A Survey of Smooth Vector Graphics: Recent Advances in Repr esentation, Creation, Rasterization, and Image Vectorization

Tian

Günther

2024

IEEE Trans. Visual. Comput. Graphics

View full text Add to dashboard Cite

show abstract

“…Image Vectorization. The vast majority of image vectorization methods for both natural [HEK21, FLB16, XSTN14, LL06, OBW * 08, SLWS07, WZGW17, XLY09, Ado17] and clipart [YCZ * 16, ZCZ * 09, Ink20, HDS * 18, DSG * 20, KL11, SBv05] images first segment the inputs into color coherent regions using semantics‐free methods similar to the ones described above, and then fit the boundary of each such region using piece‐wise smooth vector curves. As discussed above, semantics‐free segmentation methods fail to produce viewer expected regions on anti‐aliased clip‐art images; in turn, this inadequate segmentation leads to poor vectorization outcomes (Fig.…”

Section: Related Workmentioning

confidence: 99%

“…Given an input 32px anti‐aliased image (a), state of the art vectorization methods [HEK21] (b), Inkscape [Ink20] (c), and VectorMagic [Vec17] (d) produce inadequate results. Our output is well aligned with viewer expectations.…”

Section: Related Workmentioning

confidence: 99%

Subpixel Deblurring of Anti‐Aliased Raster Clip‐Art

Yang

Vining

Kheradmand

et al. 2023

Computer Graphics Forum

View full text Add to dashboard Cite

Artist generated clip-art images typically consist of a small number of distinct, uniformly colored regions with clear boundaries. Legacy artist created images are often stored in low-resolution (100x100px or less) anti-aliased raster form. Compared to anti-aliasing free rasterization, anti-aliasing blurs inter-region boundaries and obscures the artist's intended region topology and color palette; at the same time, it better preserves subpixel details. Recovering the underlying artist-intended images from their low-resolution anti-aliased rasterizations can facilitate resolution independent rendering, lossless vectorization, and other image processing applications. Unfortunately, while human observers can mentally deblur these low-resolution images and reconstruct region topology, color and subpixel details, existing algorithms applicable to this task fail to produce outputs consistent with human expectations when presented with such images. We recover these viewer perceived blur-free images at subpixel resolution, producing outputs where each input pixel is replaced by four corresponding (sub)pixels. Performing this task requires computing the size of the output image color palette, generating the palette itself, and associating each pixel in the output with one of the colors in the palette. We obtain these desired output components by leveraging a combination of perceptual and domain priors, and real world data. We use readily available data to train a network that predicts, for each antialiased image, a low-blur approximation of the blur-free double-resolution outputs we seek. The images obtained at this stage are perceptually closer to the desired outputs but typically still have hundreds of redundant differently colored regions with fuzzy boundaries. We convert these low-blur intermediate images into blur-free outputs consistent with viewer expectations using a discrete partitioning procedure guided by the characteristic properties of clip-art images, observations about the antialiasing process, and human perception of anti-aliased clip-art. This step dramatically reduces the size of the output color palettes, and the region counts bringing them in line with viewer expectations and enabling the image processing applications we target. We demonstrate the utility of our method by using our outputs for a number of image processing tasks, and validate it via extensive comparisons to prior art. In our comparative study, participants preferred our deblurred outputs over those produced by the best-performing alternative by a ratio of 75 to 8.5.

show abstract

“…Our work can be used to address the image vectorisation problem since our meshes exhibit a lot of (topological) flexibility, similar to that of meshes based on curved triangles [HEK21]. It would be a breakthrough if we could generate (feature-adaptive and hierarchical) subdivision gradient meshes automatically from raster images.…”

Section: Future Workmentioning

confidence: 99%

Feature‐Adaptive and Hierarchical Subdivision Gradient Meshes

Zhou

Hettinga

Houwink

et al. 2022

Computer Graphics Forum

Self Cite

View full text Add to dashboard Cite

Gradient meshes, an advanced vector graphics primitive, are widely used by designers for creating scalable vector graphics. Traditional variants require a regular rectangular topology, which is a severe design restriction. The more advanced subdivision gradient mesh allows for an arbitrary manifold topology and is based on subdivision techniques to define the resulting colour surface. This also allows the artists to manipulate the geometry and colours at various levels of subdivision. Recent advances allow for the interpolation of both geometry and colour, local detail following edits at coarser subdivision levels and sharp colour transitions. A shortcoming of all existing methods is their dependence on global refinement, which makes them unsuitable for real‐time (commercial) design applications. We present a novel method that incorporates the idea of feature‐adaptive subdivision and uses approximating patches suitable for hardware tessellation with real‐time performance. Further novel features include multiple interaction mechanisms and self‐intersection prevention during interactive design/editing.

show abstract

Adaptive image vectorisation and brushing using mesh colours

Cited by 5 publications

References 49 publications

A Survey of Smooth Vector Graphics: Recent Advances in Repr esentation, Creation, Rasterization, and Image Vectorization

A Survey of Smooth Vector Graphics: Recent Advances in Repr esentation, Creation, Rasterization, and Image Vectorization

Subpixel Deblurring of Anti‐Aliased Raster Clip‐Art

Feature‐Adaptive and Hierarchical Subdivision Gradient Meshes

Contact Info

Product

Resources

About