This article introduces a programmable approach to nonphotorealistic line drawings from 3D models, inspired by programmable shaders in traditional rendering. This approach relies on the assumption generally made in NPR that style attributes (color, thickness, etc.) are chosen depending on generic properties of the scene such as line characteristics or depth discontinuities, etc. We propose a new image creation model where all operations are controlled through user-defined procedures in which the relations between style attributes and scene properties are specified. A view map describing all relevant support lines in the drawing and their topological arrangement is first created from the 3D model so as to ensure the continuity of all scene properties along its edges; a number of style modules operate on this map, by procedurally selecting, chaining, or splitting lines, before creating strokes and assigning drawing attributes. Consistent access to properties of the scene is provided from the different elements of the map that are manipulated throughout the whole process. The resulting drawing system permits flexible control of all elements of drawing style: First, different style modules can be applied to different types of lines in a view; second, the topology and geometry of strokes are entirely controlled from the programmable modules; and third, 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 how style modules successfully encode stylized visual characteristics that can be applied across a wide range of models.

Figure 1. Simplified illustrations produced by our system using an indication strategy. The initial and simplified versionsare respectively on the left and on the right. The objective is to keep a few complex regions at the borders of visuallydense regions to suggest their overall complexity. AbstractWe present an approach for clutter control in NPR line drawing where measures of view and drawing complexity drive the simplification 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 simplification styles where complexity is reduced either uniformly, or in a spatially-varying manner through indication.

Muscle-based systems have the potential to provide both anatomical accuracy and semantic interpretability as compared to blendshape models; however, a lack of expressivity and differentiability has limited their impact. Thus, we propose modifying a recently developed rather expressive muscle-based system in order to make it fully-differentiable; in fact, our proposed modifications allow this physically robust and anatomically accurate muscle model to conveniently be driven by an underlying blendshape basis. Our formulation is intuitive, natural, as well as monolithically and fully coupled such that one can differentiate the model from end to end, which makes it viable for both optimization and learning-based approaches for a variety of applications. We illustrate this with a number of examples including both shape matching of three-dimensional geometry as as well as the automatic determination of a threedimensional facial pose from a single two-dimensional RGB image without using markers or depth information.

No abstract