A Subdivision-Based Representation for Vector Image Editing

Liao, Zuwei; Hoppe, Hugues; Forsyth, David; Yu, Yizhou

doi:10.1109/tvcg.2012.76

Cited by 48 publications

(3 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Their method is efficient and supports interactive color editing, material replacement, and image magnification. Besides spline functions, subdivision surfaces [16,17] are also a popular scheme for image vectorization. These methods represent images by triangle tessellations, which are easier to construct than gradient meshes.…”

Section: Vector Graphicsmentioning

confidence: 99%

Hierarchical vectorization for facial images

Fu,

Liu,

Hou

et al. 2023

Comp. Visual Media

View full text Add to dashboard Cite

The explosive growth of social media means portrait editing and retouching are in high demand. While portraits are commonly captured and stored as raster images, editing raster images is non-trivial and 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 (DCs) which characterize salient geometric features and low-frequency colors, providing a means for semantic color transfer and facial expression editing. The middle level encodes specular highlights and shadows as large, editable Poisson regions (PRs) and allows the user to directly adjust illumination by tuning the strength and changing the shapes of PRs. The top level contains two types of pixel-sized PRs for high-frequency residuals and fine details such as pimples and pigmentation. We train a deep generative model that can produce high-frequency residuals automatically. Thanks to the inherent meaning in 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) to consider illumination. The new metric, illumination-sensitive FLIP, can effectively capture salient changes in color transfer results, and is more consistent with human perception than FLIP and other quality measures for portrait images. We evaluate our method on the FFHQR dataset and show it to be effective for common portrait editing tasks, such as retouching, light editing, color transfer, and expression editing.

show abstract

Section: Vector Graphicsmentioning

confidence: 99%

Hierarchical vectorization for facial images

Fu,

Liu,

Hou

et al. 2023

Comp. Visual Media

View full text Add to dashboard Cite

show abstract

“…Gradient meshes represent complex gradients by interpolating colours over the faces of a quad mesh, making them a powerful primitive to capture the smooth colour variations of natural images [SLWS07]. However, this smooth interpolation is less effective in representing sharp colour discontinuities, which require the introduction of holes [LHM09] or closely-spaced mesh lines on either side of image edges [SLWS07]. This limitation motivates Xia et al [XLY09] and Liao et al [LHFY12] to represent the image as a piecewise-smooth surface whose control mesh aligns with strong image edges, using a multiresolution representation for the latter.…”

Section: Related Workmentioning

confidence: 99%

Vectorising Bitmaps into Semi‐Transparent Gradient Layers

Richardt

López‐Moreno

Bousseau

et al. 2014

Computer Graphics Forum

View full text Add to dashboard Cite

(c) Editing result (b) Multi-layer vector representation (a) Input photographFigure 1: Our interactive vectorisation technique lets users vectorise an input bitmap (a) into a stack of opaque and semi-transparent vector layers composed of linear or radial colour gradients (b). Users can manipulate the resulting layers using standard tools to quickly produce new looks (c). We outline semi-transparent layers for visualisation; these edges are not part of our result. We rasterised figures to avoid problems with transparency in some PDF viewers. See supplemental material for vector graphics. AbstractWe present an interactive approach for decompositing bitmap drawings and studio photographs into opaque and semi-transparent vector layers. Semi-transparent layers are especially challenging to extract, since they require the inversion of the non-linear compositing equation. We make this problem tractable by exploiting the parametric nature of vector gradients, jointly separating and vectorising semi-transparent regions. Specifically, we constrain the foreground colours to vary according to linear or radial parametric gradients, restricting the number of unknowns and allowing our system to efficiently solve for an editable semi-transparent foreground. We propose a progressive workflow, where the user successively selects a semi-transparent or opaque region in the bitmap, which our algorithm separates as a foreground vector gradient and a background bitmap layer. The user can choose to decompose the background further or vectorise it as an opaque layer. The resulting layered vector representation allows a variety of edits, such as modifying the shape of highlights, adding texture to an object or changing its diffuse colour.

show abstract

“…Their method is efficient and supports interactive color editing, material replacement and image magnification. Besides spline functions, subdivision surfaces [252,253] are also a popular scheme for image vectorization.…”

Section: Intrinsic Imagesmentioning

confidence: 99%

Towards robust natural language and image processing In low-resource scenarios

Liu¹

View full text Add to dashboard Cite

Comparison of the representations obtained at each layer before (Base) and after adapter-based tuning or fine-tuning on BERT-base using Representational Similarity Analysis (RSA). . . . . . . . . 4.3 Test performance w.r.t the number of training examples. Reported results are averages across five runs with different random seeds. . 4.4 Box plots of test performance distribution over 20 runs across different learning rates.

show abstract

A Subdivision-Based Representation for Vector Image Editing

Cited by 48 publications

References 30 publications

Hierarchical vectorization for facial images

Hierarchical vectorization for facial images

Vectorising Bitmaps into Semi‐Transparent Gradient Layers

Towards robust natural language and image processing In low-resource scenarios

Contact Info

Product

Resources

About