M
Marko Filipović
Researcher at University of Zagreb
Publications - 13
Citations - 192
Marko Filipović is an academic researcher from University of Zagreb. The author has contributed to research in topics: Sparse approximation & Inpainting. The author has an hindex of 6, co-authored 13 publications receiving 162 citations.
Papers
More filters
Journal ArticleDOI
Tucker factorization with missing data with application to low-$$n$$n-rank tensor completion
Marko Filipović,Ante Jukic +1 more
TL;DR: This paper proposes a simple algorithm for Tucker factorization of a tensor with missing data and its application to low-$$n$$n-rank tensor completion and demonstrates in several numerical experiments that the proposed algorithm performs well even when the ranks are significantly overestimated.
Journal ArticleDOI
A comparison of dictionary based approaches to inpainting and denoising with an emphasis to independent component analysis learned dictionaries
Marko Filipović,Ivica Kopriva +1 more
TL;DR: It is demonstrated that ICA-learned basis outperforms K-SVD and morphological component analysis approaches in terms of visual quality and noiseless inpainting-based approach to image Denoising greatly outperforms denoising based on two-dimensional myriad filtering that is a theoretically optimal solution for this class of additive impulsive noise.
Proceedings ArticleDOI
Restoration of images corrupted by mixed Gaussian-impulse noise by iterative soft-hard thresholding
Marko Filipović,Ante Jukic +1 more
TL;DR: Experimental evaluation suggests that the proposed patch-based approach can produce state-of-the-art results for some types of images, especially in terms of the structural similarity (SSIM) measure.
Proceedings ArticleDOI
Inpainting color images in learned dictionary
TL;DR: This work addresses the problem of patch space-based dictionary learning for color images by representing an image in RGB color space as a collection of vectorized 3D patch tensors, which leads to the state-of-the-art results in inpainting random and structured patterns of missing values.
Journal ArticleDOI
Supervised feature extraction for tensor objects based on maximization of mutual information
Ante Jukic,Marko Filipović +1 more
TL;DR: A new method for efficiently approximating the global penetration depth between two rigid objects using machine learning techniques and observing more than an order of magnitude improvement over prior PD computation techniques is presented.