Abstract | ||
---|---|---|
We facilitate the creation of 3D-looking shaded production drawings from concept sketches. The key to our approach is a class of commonly used construction curves known as cross-sections, that function as an aid to both sketch creation and viewer understanding of the depicted 3D shape. In particular, intersections of these curves, or cross-hairs, convey valuable 3D information, that viewers compose into a mental model of the overall sketch. We use the artist-drawn cross-sections to automatically infer the 3D normals across the sketch, enabling 3D-like rendering. The technical contribution of our work is twofold. First, we distill artistic guidelines for drawing cross-sections and insights from perception literature to introduce an explicit mathematical formulation of the relationships between cross-section curves and the geometry they aim to convey. We then use these relationships to develop an algorithm for estimating a normal field from cross-section curve networks and other curves present in concept sketches. We validate our formulation and algorithm through a user study and a ground truth normal comparison. As demonstrated by the examples throughout the paper, these contributions enable us to shade a wide range of concept sketches with a variety of rendering styles. |
Year | DOI | Venue |
---|---|---|
2012 | 10.1145/2185520.2185541 | ACM Trans. Graph. |
Keywords | Field | DocType |
sketch creation,artist-drawn cross-section,artistic guideline,ground truth normal comparison,cross-section curve,normal field,shading concept,overall sketch,concept sketch,explicit mathematical formulation,cross-section curve network,cross section,product design,sketch based modeling,non photorealistic rendering | Computer vision,Mental model,Sketch-based modeling,Computer graphics (images),Computer science,Non-photorealistic rendering,Ground truth,Artificial intelligence,Product design,Rendering (computer graphics),Perception,Sketch | Journal |
Volume | Issue | ISSN |
31 | 4 | 0730-0301 |
Citations | PageRank | References |
35 | 1.08 | 24 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Cloud Shao | 1 | 35 | 1.08 |
Adrien Bousseau | 2 | 795 | 39.31 |
Alla Sheffer | 3 | 3074 | 143.00 |
Karan Singh | 4 | 1529 | 76.00 |