CSAIL Research Abstracts - 2005 link to http://publications.csail.mit.edu/abstracts/abstracts05/index.html link to http://www.csail.mit.edu
bullet Introduction bullet Architecture, Systems
& Networks
bullet Language, Learning,
Vision & Graphics
bullet Physical, Biological
& Social Systems
bullet Theory bullet

horizontal line

A Procedural Approach to Style for NPR Line Drawing from 3D Models

Stéphane Grabli, Frédo Durand, Emmanuel Turquin & François Sillion

Line drawing from a  3D model Line drawing from a  3D model

The field of Non-Photorealistic Rendering has proposed a variety of techniques to create compelling line drawings from 3D models. Unfortunately, these methods are generally hard-coded in monolithic software and lack a flexible and formal specification framework. In contrast, the shading languages available in photorealistic renderers such as Pixar Renderman permit the design of an infinite variety of rich and complex appearances.


In this research, we present an approach to style in line drawing inspired by photorealistic production rendering software such as Renderman. The style of a line drawing can be specified in our approach by implementing procedures that describe how the silhouettes and other feature lines from the 3D model should be turned into strokes. Historically, the development of shading languages has dramatically facilitated the exploration and development of realistic shading, and it has contributed to a dramatic improvement in the quality of production rendering. We hope that NPR can similarly benefit from a flexible procedural approach.


We propose a new image creation model where all operations are controlled procedurally. A view map describing all relevant support lines in the drawing is first created from the 3d model; a number of style modules operate on this map, by procedurally selecting and chaining lines before creating strokes and assigning drawing attributes. Two different levels of user control are provided, ranging from a low-level programming API to a parameterized building-block assembly mechanism. The resulting drawing system allows very flexible control of all elements of drawing style: first, different style modules can be applied to different types of lines in a view; second, stroke attributes are assigned procedurally and can be correlated at will with various scene or view properties. We illustrate the components of our system and show results of its application.

Line drawing from a  3D model

We have also developed an approach for clutter control in NPR line drawing where measures of view and drawing complexity drive the simplication or omission of lines. We define two types of density information: the a-priori density and the causal density, and use them to control which parts of a drawing need simplification. The a-priori density is a measure of the visual complexity of the potential drawing and is computed on the complete arrangement of lines from the view. This measure affords a systematic approach for characterizing the structure of cluttered regions in terms of geometry, scale, and directionality. The causal density measures the spatial complexity of the current state of the drawing as strokes are added, allowing for clutter control through line omission or stylization. We show how these density measures permit a variety of pictorial simplication styles where complexity is reduced either uniformly, or in a spatially-varying manner through indication.

Image with all strokes drawn After simplification.
Picture of a house computed from a 3D model. First image: all strokes are drawn. Second Image: using our automatic simplification technique.

The current system requires programming skills and artistic training to implement a compeiling style. In order to make the approach available to a broader audience, we will develop techniques to easily capture and re-apply line drawing style. Our goal is to move from the imperative nature of our procedural system to a more natural declarative approach. The user should not specify the style in terms of "how to" produce it, but in terms of "what is" the desired appearance.

Research Support

This work was supported by an NSF CISE Research Infrastructure Award (EIA9802220) and a NEC junior research support. We also acknowledge an NSF équipe associée and an MIT France funding.

This research was conducted in collaboration with the Artis team in Grenoble, France.


[1] Stéphane Grabli, Frédo Durand, and François Sillion. Density Measure for Line-Drawing Simplification. Proceedings of Pacific Graphics 2004

[2] Stéphane Grabli, Frédo Durand, and François Stéphane Grabli, Emmanuel Turquin, Frédo Durand, and François Sillion Programmable Style for NPR Line Drawing. Proceedings of the Eurographics Symposium on Rendering 2004

[3] Stéphane Grabli, Frédo Durand, and François The code is available online through sourceforge.

horizontal line

MIT logo Computer Science and Artificial Intelligence Laboratory (CSAIL)
The Stata Center, Building 32 - 32 Vassar Street - Cambridge, MA 02139 - USA
tel:+1-617-253-0073 - publications@csail.mit.edu
(Note: On July 1, 2003, the AI Lab and LCS merged to form CSAIL.)