Space-Variant Image Deblurring on Smartphones Using Inertial Sensors

Ondrej Sindelar, Filip Sroubek, Peyman Milanfar

Abstract: Low-light hand-held photography requires long exposures and leads to space-variant blur degradation. Removing blur without any information about the camera motion is a computationally demanding and unstable process. In this demo system, we use rotational inertial sensors (gyroscopes) to detect the motion trajectory of the camera during exposure and then use it as a base for removing blur from the acquired photographs. The demo is a close-to-real-time deblurring technology, implemented on an Android smartphone.