Recognizing fine-grained categories (e.g., bird species) is difficult due to the challenges of discriminative region localization and fine-grained feature learning. In this project, we are aiming at recognizing the fine-grained image categories at a very…
By Andrew Maimone, Researcher; Andreas Georgiou, Researcher; Joel Kollin, Principal Research Hardware Development Engineer Last week at the SCIEN Workshop on Augmented and Mixed Reality, a group of industry and academic researchers met to discuss the future of…
We present novel designs for virtual and augmented reality near-eye displays based on phase-only holographic projection. For more information, please visit our project page and blog.
Summary In this project, we explore how digital holography can be used to build novel near-eye displays for virtual and mixed (or augmented) reality. We experiment with true, phase-only holograms in which the image is formed by the interference…
Video: Making Faces. An actress reads from a script designed to provide maximal phonetic coverage (we were planning to do automatic lip sync as a follow-on research project but never got around to it). Hence the…
Using a piecewise parametric representation, we have made complex procedural objects that have a memory footprint of just 7-11 KBytes, which render at approximately 20 million triangles/ sec. on an NVidia 6800 GPU.
The D* algorithm computes efficient symbolic derivatives for these functions by symbolically executing the expression graph at compile time to eliminate common subexpressions and by exploiting the special nature of the graph that represents the…
