Multiperspective Distortion Correction Using Collineations

We present a new framework for correcting multiperspective distortions using collineations. A collineation describes the transformation between the images of a camera due to changes in sampling and image plane selection. We show that image distortions in many previous models of cameras can be effectively reduced via proper collineations. To correct distortions in a specific multiperspective camera, we develop an interactive system that allows users to select feature rays from the camera and position them at the desirable pixels. Our system then computes the optimal collineation to match the projections of these rays with the corresponding pixels. Experiments demonstrate that our system robustly corrects complex distortions without acquiring the scene geometry, and the resulting images appear nearly undistorted.