Detection and Recovery of Film Dirt for Archive Restoration Applications

A novel spatio-temporal method is proposed for film dirt detection and recovery. Firstly, a more reliable confidence measurement of dirt is extracted for color films. False alarms caused by motion are filtered using consistency checks among several measurements. Then, candidate dirt is detected by filtering and thresholding this confidence measurement. Finally, bi-directional local motion compensation and ML3Dex filtering are taken for the recovery of dirt pixels. Experiments on real data demonstrate the efficiency and effectiveness of our method in terms of both detection and recovery of dirt.