Image vectorization using optimized gradient meshes

Sun, Jian; Li, Lin; Wen, Fang; Shum, Heung-Yeung

doi:10.1145/1239451.1239462

Cited by 28 publications

(63 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Techniques for the vectorization of general images make the assumption that the image content can be represented by a collection of boundary curves, together with smooth interpolating functions between the curves. In one family of approaches, the im-age is first segmented into regions by, for example, triangulation or using quad-dominant gradient meshes, and then the region interiors are filled with smooth gradients [Lecot and Lévy 2006;Sun et al 2007;Xia et al 2009]. Alternatively, using diffusion curves, the smooth interior can be computed by solving a Poisson equation with the curves as boundary constraints [Orzan et al 2008].…”

Section: Related Workmentioning

confidence: 99%

Topology-driven vectorization of clean line drawings

et al. 2013

View full text Add to dashboard Cite

Vectorization provides a link between raster scans of pencil-andpaper drawings and modern digital processing algorithms that require accurate vector representations. Even when input drawings are comprised of clean, crisp lines, inherent ambiguities near junctions make vectorization deceptively difficult. As a consequence, current vectorization approaches often fail to faithfully capture the junctions of drawn strokes. We propose a vectorization algorithm specialized for clean line drawings that analyzes the drawing's topology in order to overcome junction ambiguities. A gradientbased pixel clustering technique facilitates topology computation. This topological information is exploited during centerline extraction by a new "reverse drawing" procedure that reconstructs all possible drawing states prior to the creation of a junction and then selects the most likely stroke configuration. For cases where the automatic result does not match the artist's interpretation, our drawing analysis enables an efficient user interface to easily adjust the junction location. We demonstrate results on professional examples and evaluate the vectorization quality with quantitative comparison to hand-traced centerlines as well as the results of leading commercial algorithms.

show abstract

Section: Related Workmentioning

confidence: 99%

Topology-driven vectorization of clean line drawings

et al. 2013

View full text Add to dashboard Cite

show abstract

“…In the literature, Sun et al [4] and Lai et al [5] developed semi-automatic and automatic methods for generating gradient meshes from a raster image. Lai et al [5] extended the topology property of gradient meshes to allow an arbitrary number of holes in image objects.…”

Section: Related Workmentioning

confidence: 99%

“…Following [4,5], a normal gradient mesh is a regular planar grid of Ferguson patches [33], each containing four control points ( Fig. 3(a)).…”

Section: Gradient Mesh Representationmentioning

confidence: 99%

“…There is one thing deserving a mention: the factor α (and β) should keep its original value, although it can be estimated according to (4). This is because α and β are also used in the interpolation of mesh positions, and any change in their values may modify the shape of gradient meshes.…”

Section: Control Net For Normal Gradient Meshesmentioning

confidence: 99%

“…The weights can be efficiently computed via Dijkstra algorithm, and ǫ is empirically set as ǫ = 1. The recoloring computation has an average time complexity of O(|Ω| · |chrominances(Ω c )|) 4 . In case that the mesh is very big, we can adopt the relaxation in [24] to reduce the time complexity to O(|Ω|), which blends the two or three most significant chrominance (the chrominance with the closest intrinsic distance).…”

Section: Recoloring Using Extended Chrominance Blendingmentioning

confidence: 99%

See 2 more Smart Citations

Scribble-based gradient mesh recoloring

Wan

Xiao

Dou

et al. 2017

Multimed Tools Appl

View full text Add to dashboard Cite

Previous gradient mesh recoloring methods usually have dependencies on an additional reference image and the rasterized gradient mesh. To circumvent such dependencies, we propose a user scribble-based recoloring method, in which users are allowed to annotate gradient meshes with a few color scribbles. Our approach builds an auxiliary mesh from gradient meshes, namely control net, by taking both colors and local color gradients at mesh points into account. We then develop an extended chrominance blending method to propagate the user specified colors over the control net. The recolored gradient mesh is finally reconstructed from the recolored control net. Experiments validate the effectiveness of our approach on multiple gradient meshes. Compared with various alternative solutions, our method has no color bleedings nor sampling artifacts, and can achieve fast performance.

show abstract

Gradient Art: Creation and Vectorization

Barla

Bousseau²

2012

Computational Imaging and Vision

View full text Add to dashboard Cite

There are two different categories of methods for producing vector gradients. One is mainly interested in converting existing photographs into dense vector representations. By vector it is meant that one can zoom infinitely inside images, and that control values do not have to lie onto a grid but must represent subtle color gradients found in input images. The other category is tailored to the creation of images from scratch, using a sparse set of vector primitives. In this case, we still have the infinite zoom property, but also an advanced model of how space should be filled in-between primitives, since there is no input photograph to rely on. These two categories are actually extreme cases, and seem to exclude each other: a dense representation is difficult to manipulate, especially when one wants to modify topology; a sparse representation is hardly adapted to photo vectorization, especially in the presence of texture. Very few methods lie in the middle, and the ones that do require user assistance. The challenge is worth the effort though: it would make converting an image into vector primitives easily amenable to stylization.

show abstract

Image vectorization using optimized gradient meshes

Cited by 28 publications

References 0 publications

Topology-driven vectorization of clean line drawings

Topology-driven vectorization of clean line drawings

Scribble-based gradient mesh recoloring

Gradient Art: Creation and Vectorization

Contact Info

Product

Resources

About