Peter C. Litwinowicz

Processing images and video for an impressionist effect

This paper describes a technique that transforms ordinary video segments into animations that have a hand-painted look. Our method is the first to exploit temporal coherence in video clips to design an automatic filter with a hand-drawn animation quality, in this case, one that produces an Impressionist effect. Off-the-shelf image processing and rendering techniques are employed, modified and combined in a novel way. This paper proceeds through the process step by step, providing helpful hints for tuning the off-the-shelf parts as well as describing the new techniques and bookkeeping used to glue the parts together.

Animating images with drawings

The work described here extends the power of 2D animation with a form of texture mapping conveniently controlled by line drawings. By tracing points, line segments, spline curves, or filled regions on an image, the animator defines features which can be used to animate the image. Animations of the control features deform the image smoothly. This development is in the tradition of “skeleton”-based animation, and “feature”-based image metamorphosis. By employing numerics developed in the computer vision community for rapid visual surface estimation, several important advantages are realized. Skeletons are generalized to include curved “bones,” the interpolating surface is better behaved, the expense of computing the animation is decoupled from the number of features in the drawing, and arbitrary holes or cuts in the interpolated surface can be accommodated. The same general scattered data interpolation technique is applied to the problem of mapping animation from one image and set of features to another, generalizing the prescriptive power of animated sequences and encouraging reuse of animated motion.

Constraint-based motion adaptation

Todays computer animators have access to many systems and techniques to author high-quality motion. Unfortunately, available techniques typically produce a particular motion for a specific character. In this paper we present a constraint-based approach to adapt previously created motions to new situations and characters. We combine constraint methods that compute changes to motion to meet specified needs with motion signal processing methods that modify signals yet preserve desired properties of the original motion. The combination allows the adaptation of motions to meet new goals while retaining much of the motions original quality.

Facial Animation by Spatial Mapping

This paper describes a means for generating facial animation. Motion is captured on video from the actions of a live performer. Control points are obtained from the video, and this acquired motion is spatially mapped to conform to a synthetic actor’s face. The mapping takes into account differences in proportions between the two faces. Animation is then generated by deforming the texture and geometry of the synthetic face around the control points. This technique was used in “The Audition” to animate a talking dog.

Inkwell: A 2-D animation system

Inkwell, an experimental 2 1/2-D keyframe animation system, is the subject of this paper. Inkwell provides an intuitive user interface for creating and animating polygons, ellipses and splines. These primitives may be outlined and filled with a variety of patterns to create animated diagrams, graphs and charts, and simple characters and cartoons. Inkwell also has a patch primitive that facilitates deformation and animation of textured regions. The system provides editing features that include shape and timing control as well as digital filtering of parameters. Finally, Inkwell has deformation primitives that enable an animator to warp geometry in an intuitive manner. Inkwell was used to produce Pigment Promenade, a computer animated short shown at SIGGRAPH 1990.

Efficient techniques for interactive texture placement

This paper describes efficient algorithms for the placement and distortion of textures. The textures include surface color maps and environment maps. Affine transformations of a texture, as well as localized warps, are used to align features in the texture with features of the model. Image-space caches are used to enable texture placement in real time.

A semi-automatic system for edge tracking with snakes

Active contour models, or “snakes,” developed in (Kass et al. 1988), use a simple physical model to track edges in image sequences. Snakes as originally defined however, tend to shrink, stretch and slide back and forth in unwanted ways along a tracked edge and are also confused by multiple edges, always grabbing the nearest one. In this paper a semi-automatic system is presented that combines motion estimation techniques with snakes to overcome these problems. An algorithm is presented that uses a block matching technique to guide the endpoints of the snake, optical flow to push the snake in the direction of the underlying motion, followed by the traditional snake edge-fitting minimization process. We use this technique for tracking facial features of an actor for driving computer animated characters.

Impressions of San Francisco

V IS U A L P R O C E E D IN G S 268 “Inherited Memories” explores the intertwining and transformation of photographic 2D compositing extended into animation. Based on photographs from Prague, Warsaw, and Krakow, it is a documentation of an imagined cultural past, built from layers of memories of times beyond personal experience. Producer: Cynthia Beth Rubin Contributors: Cynthia Beth Rubin, Bob Gluck Inherited Memories