Data Set Used
We introduce the concept of a Pixel Stream Editor. This forms the basis for an interactive synthesizer for designing highly realistic Computer Generated Imagery. The designer works in an interactive Very High Level programming environment which provides a very fast concept/implement/view iteration cycle.Naturalistic visual complexity is built up by… (More)
We present a novel method for real-time continuous pose recovery of markerless complex articulable objects from a single depth image. Our method consists of the following stages: a randomized decision forest classifier for image segmentation, a robust method for labeled dataset generation, a convolutional network for dense feature extraction, and finally an… (More)
We believe that navigation in information spaces is best supported by tapping into our natural spatial and geographic ways of thinking. To this end, we are developing a new computer interface model called Pad. The ongoing Pad project uses a spatial metaphor for computer interface design. It provides an intuitive base for the support of such applications as… (More)
All of these media have one thing in common. Every moment of the audience's journey is being guided by talented experts, whether an screenwriter and actor/director, a writer/animator, or a playwright and team of puppeteers. These experts use their judgment to maintain a balance: characters must be consistent and recognizable, and must respond to each other… (More)
Building on principles from our prior work on procedural texture synthesis, we are able to create remarkably lifelike, responsively animated characters in real time. Rhythmic and stochastic noise functions are used to deene time varying parameters that drive computer generated puppets. Because we are conveying just the \texture" of motion, we are able to… (More)
We describe Pad++, a zoomable graphical sketchpad that we are exploring as an alternative to traditional window and icon-based interfaces. We discuss the motivation for Pad++, describe the implementation, and present prototype applications. In addition, we introduce an informational physics strategy for interface design and briefly contrast it with current… (More)
We present a " heads-up " shorthand for entering text on a stylus-based computer very rapidly. The innovations are that (i) the stylus need never be lifted from the surface, and that (ii) the user need never stop moving the stylus. Continuous multi-word text of arbitrary length can be written fluidly, even as a single continuous gesture if desired.
Two deficiencies in the original Noise algorithm are corrected: second order interpolation discontinuity and unoptimal gradient computation. With these defects corrected, Noise both looks better and runs faster. The latter change also makes it easier to define a uniform mathematical reference standard.
We present new methods for painterly video processing. Based on our earlier still image processing technique, we " paint over " successive frames of animation, applying paint only in regions where the source video is changing. Image regions with minimal changes, such as due to video noise, are also left alone, using a simple difference masking technique.… (More)