|
MIT Computer Science and Artificial Intelligence Lab (CSAIL)
Abstract:
I'll present two recent research projects from my group. (They're unrelated, except that I'm excited about both of them. One was selected to be an oral presentation at NIPS, the other was rejected from the conference. See if you can guess which was which.) (1) Analysis of Contour Motions, by Ce Liu, William Freeman, and Edward Adelson. A reliable motion estimation algorithm must function under a wide range of conditions. One regime, which we consider here, is the case of moving objects with contours but no visible texture. It is difficult to determine the reliability of motion from local measurements, since seemingly reliable local motion evidence can result from both real and spurious features. We propose a novel approach that derives global motion estimates by utilizing information from three levels of contour analysis: edgelets, boundary fragments and contours. Our system is successfully applied to both synthetic and real video sequences containing high-contrast boundaries and textureless regions. The system produces good motion estimates along with properly grouped and completed contours. (2) Random Lens Imaging, by Antonio Torralba, Rob Fergus, and William Freeman. We call a random lens one for which the function relating the input light ray to the output sensor location is pseudo-random. Imaging systems with random lenses can expand the space of possible camera designs, allowing new trade-offs in optical design and potentially adding new imaging capabilities. Machine learning methods are critical for both camera calibration and image reconstruction from the sensor data. We develop the theory and compare two different methods for calibration and reconstruction: an MAP approach, and basis pursuit from compressive sensing. We show proof-of-concept experimental results from a random lens made from a multi-faceted mirror, showing successful calibration and image reconstruction. We illustrate the potential for super-resolution and 3D imaging.