Pixel Club: Calibration of Multi-Camera Systems by Global Constraints on the Motion of Silhouettes
- Gil Ben-Artzi (Weizmann Institute of Science)
- Thursday, 5.1.2017, 10:30
- EE Meyer Building 1061
Computing the epipolar geometry between cameras with very different viewpoints is often problematic as matching points are hard to find. In these cases, it has been proposed to use information from dynamic objects in the scene for suggesting point and line correspondences. We introduce an approach that improves by two orders of magnitude the performance over state-of-the-art methods, by significantly reducing the number of outliers in the putative matches. Our approach is based on (a) a novel method to *directly* recover corresponding epipolar lines across views without access to the fundamental matrix, and (b) formulation of the correspondences problem as constrained flow optimization, providing efficient optimal iterative solution. Our method was validated on four standard datasets providing accurate calibrations across very different viewpoints.