Modeling Character Canvases from Cartoon Drawings

Abstract

We introduce a novel technique for the construction of a 3D character proxy, or canvas , directly from a 2D cartoon drawing and a user-provided correspondingly posed 3D skeleton. Our choice of input is motivated by the observation that traditional cartoon characters are well approximated by a union of generalized surface of revolution body parts, anchored by a skeletal structure. While typical 2D character contour drawings allow ambiguities in 3D interpretation, our use of a 3D skeleton eliminates such ambiguities and enables the construction of believable character canvases from complex drawings. Our canvases conform to the 2D contours of the input drawings, and are consistent with the perceptual principles of Gestalt continuity, simplicity, and contour persistence. We first segment the input 2D contours into individual body-part outlines corresponding to 3D skeletal bones using the Gestalt continuation principle to correctly resolve inter-part occlusions in the drawings. We then use this segmentation to compute the canvas geometry, generating 3D generalized surfaces of revolution around the skeletal bones that conform to the original outlines and balance simplicity against contour persistence. The combined method generates believable canvases for characters drawn in complex poses with numerous inter-part occlusions, variable contour depth, and significant foreshortening. Our canvases serve as 3D geometric proxies for cartoon characters, enabling unconstrained 3D viewing, articulation, and non-photorealistic rendering. We validate our algorithm via a range of user studies and comparisons to ground-truth 3D models and artist-drawn results. We further demonstrate a compelling gallery of 3D character canvases created from a diverse set of cartoon drawings with matching 3D skeletons.

Structuring and layering contour drawings of organic shapes

“…Note that for Figure 20, we reused drawings from a recent paper [Bessmeltsev et al 2015], showing that our method achieves the structuring and layering of such drawings without the need of any extra information, whereas a user-defined 3D skeleton was used in the original paper. Figures 1 and 14 (top-right) show even more challenging cases where some of the suggestive contours form a chain of T-junctions, requiring the labeling method of Section 6.2 in order to be properly processed.…”

“…Figure 20: Results on three drawings also used in [Bessmeltsev et al 2015], except that we removed the hat of the character. Warmer colors are in the foreground.…”

“…Given that a drawing is only composed of lines, several approaches have been proposed to identify which visual mechanisms are used to help interpret the drawn lines in terms of self-consistent shapes and contours [Singh 2015].…”

“…Most methods in the area built on a priori knowledge (or contextual information) in order to resolve ambiguities -such as requiring exact symmetric shapes [Cordier et al 2011], being restricted to garments [Turquin et al 2007] or to side views of animals [Entem et al 2014] or requesting 3D information such as a 3D skeleton from the user [Bessmeltsev et al 2015]. Others methods obtained great results by relying on interactive user annotations for helping to infer high-reliefs from photos or drawings [Bui et al 2015;Rivers et al 2010;Sýkora et al 2014;Yeh et al 2017].…”

Medialness and the Perception of Visual Art

“…The use of a simplified MA in the form of a stick figure as a drawing interface has been proposed before, for example to access large datasets of human motion data (Choi et al, 2012). Alternatively, from a drawn 2D cartoon character, a simplified MA can be automatically recovered and then used to deform and animate a corresponding 3D extruded version (Igarashi et al, 1999) or even generate a 3D character proxy which can then be further manipulated by the artist (Bessmeltsev et al, 2015).…”