Computer vision has been an active research area for the past 30 years. Finding tractable mathematical formulations of many tasks humans take for granted has proven hard and getting the algorithms working in the real world have proven harder.
We believe much of the problem stems from immaturity of basic computer vision techniques for establishing relationships between images. This is a necessary step for fusing information across multiple images.
This website documents our attempts to fix this long-standing problem. We present fundamentally different approaches to classic problems like clustering and feature matching, with significant performance gains.