Learn More
Given multiple time sequences with missing values, we propose <b>DynaMMo</b> which summarizes, compresses, and finds latent variables. The idea is to discover hidden variables and learn their dynamics, making our algorithm able to function even when there are missing values. We performed experiments on both real and synthetic datasets spanning several(More)
By changing only the playback timing of a motion sequence, an animator can achieve a variety of effects that alter our perception of an event. In some scenarios, it may be important to consider physical properties of the motion when retiming (e.g., to preserve physical plausibility). However, existing retiming solutions can be quite time consuming when(More)
Given two motion-capture sequences that are to be stitched together, how can we assess the goodness of the stitching? The straightforward solution, Euclidean distance, permits counter-intuitive results because it ignores the effort required to actually make the stitch. The main contribution of our work is that we propose an intuitive, first-principles(More)
In a conventional 2d painting or compositing program, graphical objects are stacked in a user-specified global order, as if each were printed on an image-sized sheet of transparent film. In this paper we show how to relax this restriction so that users can make stacking decisions on a per-overlap basis, as if the layers were pictures cut from a magazine.(More)
Since the seminal SketchPad work of Sutherland [1964], direct interaction with a computer has been compelling: we can directly touch, move, and change what we see. Direct interaction is a major contribution to the success of smartphones and tablets; yet, the world is not flat. While existing technologies can display realistic multi-view stereoscopic 3D(More)
Given a motion capture sequence with occlusions, how can we recover the missing values, respecting bone-length constraints? Recent past work uses Linear Dynamical Systems (LDS), which work well, except for occasionally violating such constraints, and thus lead to unrealistic results. Our main contribution is a principled approach for preserving such(More)
We present a new type of 3D printer that can form precise, but soft and deformable 3D objects from layers of off-the-shelf fabric. Our printer employs an approach where a sheet of fabric forms each layer of a 3D object. The printer cuts this sheet along the 2D contour of the layer using a laser cutter and then bonds it to previously printed layers using a(More)
Figure 1: Our mid-level fluid control system allows artists to specify local smoke behavior by providing density motifs (left). The resulting fluid can be integrated with 2D animations (center left). In this case, we have recolored the smoke to match the wand colors. Other effects our system can generate (center right) include global textures such as clouds(More)