Abstract: Methods and apparatus for 3D sketching may provide an interface for creating 3D drawings from 2D and 3D input, and for creating 3D curve networks. The technique may provide tools for 2D sketching that enable 2D sketching in 3D space, and for creating a network of intersecting 3D curves. The technique may provide user interface elements and techniques that facilitate the curve drawing tasks. For 2D sketching, the technique may provide methods for interpreting imprecise user 2D strokes as continuous, high-quality 3D curves. The technique may provide the ability to edit existing 3D curves using sketched 2D strokes. The technique may enable sketching of 3D curves by rotating a drawing plane and/or by creating drawing surfaces on which curves may be added. The technique may provide user interface elements for converting curves in 3D space into a curve network.

Abstract: Methods and apparatus for 3D sketching may provide an interface for creating 3D drawings from 2D and 3D input, and for creating 3D curve networks. The technique may provide tools for 2D sketching that enable 2D sketching in 3D space, and for creating a network of intersecting 3D curves. The technique may provide user interface elements and techniques that facilitate the curve drawing tasks. For 2D sketching, the technique may provide methods for interpreting imprecise user 2D strokes as continuous, high-quality 3D curves. The technique may provide the ability to edit existing 3D curves using sketched 2D strokes. The technique may enable sketching of 3D curves by rotating a drawing plane and/or by creating drawing surfaces on which curves may be added. The technique may provide user interface elements for converting curves in 3D space into a curve network.

Abstract: The method captures a 3D model of a face, which includes a 3D mesh and a series of deformations of the mesh that define changes in position of the mesh over time (e.g., for each frame). The method also builds a texture map associated with each frame in an animation sequence. The method achieves significant advantages by using markers on an actor's face to track motion of the face over time and to establish a relationship between the 3D model and texture. Specifically, videos of an actor's face with markers are captured from multiple cameras. Stereo matching is used to derive 3D locations of the markers in each frame. A 3D scan is also performed on the actor's face with the markers to produce an initial mesh with markers. The markers from the 3D scan are matched with the 3D locations of the markers in each frame from the stereo matching process. The method determines how the position of the mesh changes from frame to frame by matching the 3D locations of the markers from one frame to the next.