2004 · 16 citations · 3 references
ComputingComputer ScienceComputer VisionDigital ImagingMachine VisionDigital Image ProcessingImage RestorationImage TextureMotion AnalysisMotion EstimationVideo AnalysisBlendingDisparity MetricsLinear InterpolationMotion Artifact DetectionSpatio-temporal RepresentationVideo Inpainting
Spikes of brightness often locally affect single frames of aged motion pictures, because of dust, dirt and scratches injuring the film surface. We present a method for accurate digital detection and restoration of such kinds of film defects. The method evaluates both global and local intraframe disparity statistics after motion-compensation and uses them to detect abnormal spikes. It recovers image structure from the same frame by linear interpolation of defect surroundings and refines details from the temporal neighbourhood. Weights of the blending filter are set according to local reliability of the motion estimation maps. A texture pattern is also extracted from spatial support areas, and added to regions with limited recovery from the temporal neighbourhood. Experiments performed on synthetic sequences show very high recall and precision rates, and low recovery errors. High quality restoration of severely damaged sequences is shown.
3
Automatic Restoration Algorithms for 35 mm Film
Peter Schallauer, Axel Pinz, Werner Haas · 1999 · 43 citations
Image processing for restoration of heavily-corrupted old film sequences
Takahiro Saito, Takashi Komatsu, T. Ohuchi et al. · 2002 · 16 citations