Integer‐Grid Sketch Simplification and Vectorization

Abstract

a) input line drawing and mask b) stroke-aligned parametrization c) output curve network a) input line drawing and mask b) s a) input line drawing and mask a) input line drawing and mask ask b) stroke-aligned parametrization e drawing and mask b) stroke-aligned par and mask b) stroke-aligned parametrizati igned parametrization c) output curve n b) stroke-aligned parametrization roke-aligned parametrization c) output Figure 1: Starting from an input line drawing (left), we locally parametrize the sketch as a grid aligned with the strokes (middle). Neighboring parallel strokes are automatically snapped to the same isoline of the parametrization, while junctions are snapped to grid nodes. This parametrization facilitates the extraction of a clean network of Bézier curves (right). Using a simple mask, the user can locally specify the desired amount of simplification in the output (purple scribbles: less simplification, orange scribbles: more simplification). See supplemental materials for a result without the mask.

Color by Numbers: Interactive Structuring and Vectorization of Sketch Imagery

“…Data-driven techniques, using CNNs to better group stroke pixels have also been explored [28,31]. More recently, a grid-based approach to vectorizing raster input has been considered [29]. Designed for automation, these approaches have global parameters that can impact the overall output, but are generally ill-suited to messy sketches with local variation and inaccuracies (Figure 2).…”

“…Such tools have a "low threshold" allowing even children to accomplish simple tasks quickly, and "high ceiling" providing enough control for professional quality work. Examples of such tools span [8], [28], [23], [31], [29], and our approach (left to right), given Figure 1(a) as input.…”

“…We frst segment the poly-line at sharp corners by fnding points of large change in discrete curvature [18]. We then perform an end-point interpolating, iterative least-squares cubic Bezier ft to each segment S [29], minimizing error ϵ =…”

“…Figure 2: Comparison to prior-art[8],[28],[23],[31],[29], and our approach (left to right), given Figure1(a) as input.…”

Keypoint-driven line drawing vectorization via PolyVector flow

“…Traditional vectorization approaches relied on 1-skeleton [Favreau et al 2016;Noris et al 2013] or gradient [Noris et al 2013]. A recent line of work robustly disambiguates directions around junctions via a frame field [Bessmeltsev and Solomon 2019;Stanko et al 2020]. Their frame field attaches two directions to each pixel, so that at least one of the directions is aligned to the curve tangent.…”