A Fast Model-Based Restoration of Colour Movie Scratches
 
Michal Haindl     Jiri Filip
This work presents a new type of scratch removal algorithm based on a causal adaptive multidimensional multitemporal prediction. The predictor use available information from the neighbourhood of a missing multispectral pixel due to spectral, temporal and spatial correlation of video data but not any information from the failed pixel itself. The model assumes white Gaussian noise in each spectral layer, but layers can be mutually correlated. A significant improvement of the 3D model performance is obtained if the temporal information is included, i.e., using the 3.5D causal AR model. Such information is natural to obtain from previous or/and following frame(s) for which we know all necessary data, due to high between-frame temporal correlation. Thanks to this we can treat data from different frames (specified by the contextual neighbourhood) in the same way, so we attach to each data information about its shift according to predicted pixel placement. The contextual neighbourhood has to be causal (in the reconstructed frame lattice subspace) . It means that the predictor can use only data from the model history. Then if we assume normal-Wishart parameter prior the predictor have analytical (not iterative) solution.
Scratch restoration algorithm - 4 identical 3.5D causal auroregressive models.




Results

3D CAR model - known data from the actual frame only
3.5D CAR model - known data from the actual and the previous frame

Original The
scratch		 Linear
interpolation		 3D CAR
model 		3.5D CAR model
without motion compensation		 3.5D CAR model
with motion compensation
Method comparison with classical restoration methods.

The
scratch		 Averaging Median
filtering		 Linear
interpolation		 3D CAR
model 		3.5D CAR
model
The
scratch		 Averaging Median
filtering		 Linear
interpolation		 3D CAR
model 		3.5D CAR
model




Further information can be found in the papers:
Haindl, M. - Filip, J.
Fast Restoration of Colour Movie Scratches
In: Proceedings of the 16th IAPR Int. Conf. on Pattern Recognition, Quebec City 2002,
R. Kasturi, D. Laurendeau, C. Suen Eds.,
ISBN 0-7695-1699-8, ISSN 1051-4651, vol. III,
pp. 269 - 272, IEEE Press.
Haindl, M. - Filip, J.
A Fast Model-Based Restoration of Colour Movie Scratches
In: (Research Report No. 2031). UTIA AV CR, Praha 2001, 22 pp.
 












   Back to the demonstration page.