Freeform vector graphics with controlled thin-plate splines

FinchMark,; SnyderJohn,; HoppeHugues,

doi:10.1145/2070781.2024200

Cited by 63 publications

(43 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Jeschke et al [2011] extended diffusion curves with more general color and texture functions, as well as leveraging an alternative formulation of the problem as a solution to 2D Laplace equations with Dirichlet boundary conditions. Finch et al [2011] employed higher-order profile functions based on thin-plate splines with userspecifiable discontinuities. Sun et al [2012] proposed Green's functions based representation for diffusion curves that support fast reconstruction.…”

Section: Related Workmentioning

confidence: 99%

“…Through these strategies, we reduce the number of unknowns and highly accelerate the computation. [Finch et al 2011].…”

Section: Solving For Laplacian and Bilaplacian Weightsmentioning

confidence: 99%

“…Diffusion curve images (DCI) [Orzan et al 2008], and their recent freeform vector graphics (FFG) extension [Finch et al 2011], are an expressive tool for vector image authoring. Artists sketch curves and set color constraints, and a solver "diffuses" colors perpendicularly to the curves, respecting their boundaries, to create an image.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Hierarchical diffusion curves for accurate automatic image vectorization

et al. 2014

View full text Add to dashboard Cite

Figure 1:We are able to accurately vectorize raster images ("Input") by automatically tracing a sparse set of multi-scale diffusion curves to a broad class of images, including vector art (i.e., diffusion curve images), fluid simulations with turbulent flows, and natural images. AbstractDiffusion curve primitives are a compact and powerful representation for vector images. While several vector image authoring tools leverage these representations, automatically and accurately vectorizing arbitrary raster images using diffusion curves remains a difficult problem. We automatically generate sparse diffusion curve vectorizations of raster images by fitting curves in the Laplacian domain. Our approach is fast, combines Laplacian and bilaplacian diffusion curve representations, and generates a hierarchical representation that accurately reconstructs both vector art and natural images. The key idea of our method is to trace curves in the Laplacian domain, which captures both sharp and smooth image features, across scales, more robustly than previous image-and gradientdomain fitting strategies. The sparse set of curves generated by our method accurately reconstructs images and often closely matches tediously hand-authored curve data. Also, our hierarchical curves are readily usable in all existing editing frameworks. We validate our method on a broad class of images, including natural images, synthesized images with turbulent multi-scale details, and traditional vector-art, as well as illustrating simple multi-scale abstraction and color editing results.

show abstract

Section: Related Workmentioning

confidence: 99%

“…Through these strategies, we reduce the number of unknowns and highly accelerate the computation. [Finch et al 2011].…”

Section: Solving For Laplacian and Bilaplacian Weightsmentioning

confidence: 99%

See 1 more Smart Citation

Hierarchical diffusion curves for accurate automatic image vectorization

et al. 2014

View full text Add to dashboard Cite

show abstract

“…While a small portion of the methods [Levy 2003;Das et al 2005;Finch and Hoppe 2011;Nealen et al 2007;Rose 2007;Abbasinejad et al 2011] can operate on arbitrarily shaped curves, the majority assume that the cycle is pre-segmented into n sub-curves and has a low-distortion mapping to a convex planar n-sided polygon, e.g. [Coons 1964;Gao and Rockwood 2005;Várady et al 2011].…”

Section: Surface Fitting To Curve Cyclesmentioning

confidence: 99%

Design-driven quadrangulation of closed 3D curves

et al. 2012

View full text Add to dashboard Cite

(e) design-driven quadrangulation AbstractWe propose a novel, design-driven, approach to quadrangulation of closed 3D curves created by sketch-based or other curve modeling systems. Unlike the multitude of approaches for quad-remeshing of existing surfaces, we rely solely on the input curves to both conceive and construct the quad-mesh of an artist imagined surface bounded by them. We observe that viewers complete the intended shape by envisioning a dense network of smooth, gradually changing, flow-lines that interpolates the input curves. Components of the network bridge pairs of input curve segments with similar orientation and shape. Our algorithm mimics this behavior. It first segments the input closed curves into pairs of matching segments, defining dominant flow line sequences across the surface. It then interpolates the input curves by a network of quadrilateral cycles whose iso-lines define the desired flow line network. We proceed to interpolate these networks with all-quad meshes that convey designer intent. We evaluate our results by showing convincing quadrangulations of complex and diverse curve networks with concave, non-planar cycles, and validate our approach by comparing our results to artist generated interpolating meshes.

show abstract

“…The coefficients matrix of the energy is the discrete biharmonic operator Q = LM −1 L. The matrices L and M are the stiffness matrix and the diagonal mass matrix, respectively, of the discretization mesh Ω [Pinkall and Polthier 1993]: [Levin et al 2004;Lischinski et al 2006], Global represents [Farbman et al 2010] and related approaches that use global affinity, BBW is [Jacobson et al 2011], and Biharmonic represents unbounded biharmonic interpolation [Finch et al 2011].…”

Section: Content-aware Bounded Biharmonic Weightsmentioning

confidence: 99%

Transfusive image manipulation

et al. 2012

View full text Add to dashboard Cite

Figure 1: A trained artist makes detailed edits to a single source image (left) and our method transfers the edits to the 8 target images (right). AbstractWe present a method for consistent automatic transfer of edits applied to one image to many other images of the same object or scene. By introducing novel, content-adaptive weight functions we enhance the non-rigid alignment framework of Lucas-Kanade to robustly handle changes of view point, illumination and non-rigid deformations of the subjects. Our weight functions are content-aware and possess high-order smoothness, enabling to define high-quality image warping with a low number of parameters using spatially-varying weighted combinations of affine deformations. Optimizing the warp parameters leads to subpixel-accurate alignment while maintaining computation efficiency. Our method allows users to perform precise, localized edits such as simultaneous painting on multiple images in real-time, relieving them from tedious and repetitive manual reapplication to each individual image.

show abstract

Freeform vector graphics with controlled thin-plate splines

Cited by 63 publications

References 34 publications

Hierarchical diffusion curves for accurate automatic image vectorization

Hierarchical diffusion curves for accurate automatic image vectorization

Design-driven quadrangulation of closed 3D curves

Transfusive image manipulation

Contact Info

Product

Resources

About