Single-view sketch based modeling

Abstract

This paper presents a new sketch modeling system that is able to generate complex objects drawn from a unique viewpoint. The user draws the model in an iterative manner, adding simple parts to the existing object until completion. Each part is constructed from two construction lines (lines on the surface of the object that are planar and perpendicular to each other) whose orientation in the 3D space is uniquely determined by the system, and an optional silhouette. The system is then able to produce rough 3D reconstructions of drawings very easily by tracing over a sketch for example. Such models are perfectly suited to investigate their shade or shadow and they can be used as substitutes for more detailed models when the need for quick models is present. The user can also explore shapes directly on the system, refining the shape on the go in a oversketching way. The creation of models is very efficient, as the user models the shapes directly in the correct pose and orientation. Results show that the system is able to create complex objects without ever having to change the viewpoint.

3D-look shading from contours and hatching strokes

“…This system constructs a 3D model by combining parts selected from a database by means of shadow guidance. More recently, several approaches have been proposed for directly obtaining a comprehensive 3D model using sketching strokes from a single view [14][15][16][17][18][19][20][21]. These methods provide artists with a more familiar workflow from 2D to 3D modeling.…”

True2Form

“…Past sketch based modeling methods [Andre and Saito 2011;Shao et al 2012] have used a subset of descriptive curves called crosssections. Cross-sections are planar curves, assumed to have orthogonal planes and tangents at intersections.…”

“…The space of shapes described strictly by these curves is somewhat narrow (Figure 20, first row). This space is further narrowed by [Andre and Saito 2011], who make additional regularity assumptions on the curve networks. Shao et al [2012] infer cross-sections as a step towards estimating a 3D normal field, rather than a 3D curve network.…”

3-Sweep

“…Some of these methods have limited application ranges, e.g. [Debevec et al 1996;Jiang et al 2009;Arikan et al 2013] consider architectural images, while others are restricted to non-oblique views and extrusion/inflation [Olsen and Samavati 2010], or do not guarantee to make the resulting model a precise match to the input image [Schmidt et al 2009;Andre and Saito 2011]. Yet others require extensive interaction and annotation, to allow more complicated shapes.…”