Tracking and MAP Reconstruction of line scratches in degraded motion pictures
Machine Vision and Applications - Special issue: IEEE WACV
Video Repairing under Variable Illumination Using Cyclic Motions
IEEE Transactions on Pattern Analysis and Machine Intelligence
Object Removal By Cross Isophotes Exemplar-based Inpainting
ICPR '06 Proceedings of the 18th International Conference on Pattern Recognition - Volume 03
Image inpainting based on scene transform and color transfer
Pattern Recognition Letters
Image restoration based on the fast marching method and block based sampling
Computer Vision and Image Understanding
Non-local kernel regression for image and video restoration
ECCV'10 Proceedings of the 11th European conference on computer vision conference on Computer vision: Part III
Learning non-local range Markov Random field for image restoration
CVPR '11 Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition
Region filling and object removal by exemplar-based image inpainting
IEEE Transactions on Image Processing
A robust patch-statistical active contour model for image segmentation
Pattern Recognition Letters
Human Object Inpainting Using Manifold Learning-Based Posture Sequence Estimation
IEEE Transactions on Image Processing
Hi-index | 0.10 |
In this paper, the accurate method for texture reconstruction with non-desirable moving objects into dynamic scenes is proposed. This task is concerned to editor off-line functions, and the main criteria are the accuracy and visibility of the reconstructed results. The method is based on a spatio-temporal analysis and includes two stages. The first stage uses a feature points tracking to locate the rigid objects accurately under the assumption of their affine motion model. The second stage involves the accurate reconstruction of video sequence based on texture maps of smoothness, structural properties, and isotropy. These parameters are estimated by three separate neural networks of a back propagation. The background reconstruction is realized by a tile method using a single texton, a line, or a field of textons. The proposed technique was tested into reconstructed regions with a frame area up to 8-20%. The experimental results demonstrate more accurate inpainting owing to the improved motion estimations and the modified texture parameters.