Curated Papers:
A non-local algorithm for image denoising
We propose a new measure, the method noise, to evaluate and compare the performance of digital image denoising methods. We first compute and analyze this method noise for a wide class of denoising algorithms, namely the local smoothing filters. Second, we propose a new algorithm, the nonlocal means (NL-means), based on a nonlocal averaging of all pixels in the image. Finally, we present some experiments comparing the NL-means algorithm and the local smoothing filters.
Fields of Experts: a framework for learning image priors
We develop a framework for learning generic, expressive image priors that capture the statistics of natural scenes and can be used for a variety of machine vision tasks. The approach extends traditional Markov random field (MRF) models by learning potential functions over extended pixel neighborhoods. Field potentials are modeled using a Products-of-Experts framework that exploits nonlinear functions of many linear filter responses. In contrast to previous MRF approaches all parameters, including the linear filters themselves, are learned from training data. We demonstrate the capabilities of this Field of Experts model with two example applications, image denoising and image inpainting, which are implemented using a simple, approximate inference scheme. While the model is trained on a generic image database and is not tuned toward a specific application, we obtain results that compete with and even outperform specialized techniques.
Full List:
- A non-local algorithm for image denoising A. Buades;B. Coll;J.-M. Morel Publication Year: 2005,Page(s):60 – 65 vol. 2 Cited by: Papers (2205) | Patents (77)
- A Bayesian hierarchical model for learning natural scene categories L. Fei-Fei;P. Perona Publication Year: 2005,Page(s):524 – 531 vol. 2 Cited by: Papers (1213) | Patents (38) )
- Accurate and efficient stereo processing by semi-global matching and mutual information H. Hirschmuller Publication Year: 2005,Page(s):807 – 814 vol. 2 Cited by: Papers (485) | Patents (33) )
- Fields of Experts: a framework for learning image priors S. Roth;M.J. Black Publication Year: 2005,Page(s):860 – 867 vol. 2 Cited by: Papers (389) | Patents (15)
- Object recognition with features inspired by visual cortex T. Serre;L. Wolf;T. Poggio Publication Year: 2005,Page(s):994 – 1000 vol. 2 Cited by: Papers (373) | Patents (19)
- ARTag, a fiducial marker system using digital techniques M. Fiala Publication Year: 2005,Page(s):590 – 596 vol. 2 Cited by: Papers (315) | Patents (11)
- Spectral segmentation with multiscale graph decomposition T. Cour;F. Benezit;J. Shi Publication Year: 2005,Page(s):1124 – 1131 vol. 2 Cited by: Papers (291) | Patents (7) )
- Recognizing facial expression: machine learning and application to spontaneous behavior M.S. Bartlett;G. Littlewort;M. Frank;C. Lainscsek;I. Fasel;J. Movellan Publication Year: 2005,Page(s):568 – 573 vol. 2 Cited by: Papers (274) | Patents (3)
- Ensemble tracking S. Avidan Publication Year: 2005,Page(s):494 – 501 vol. 2 Cited by: Papers (224) | Patents (1)
- Randomized trees for real-time keypoint recognition V. Lepetit;P. Lagger;P. Fua Publication Year: 2005,Page(s):775 – 781 vol. 2 Cited by: Papers (202) | Patents (26)
- Spatiograms versus histograms for region-based tracking S.T. Birchfield;Sriram Rangarajan Publication Year: 2005,Page(s):1158 – 1163 vol. 2 Cited by: Papers (196) | Patents (10)
- Robust object detection via soft cascade L. Bourdev;J. Brandt Publication Year: 2005,Page(s):236 – 243 vol. 2 Cited by: Papers (165) | Patents (37)
- Appearance modeling for tracking in multiple non-overlapping cameras O. Javed;K. Shafique;M. Shah Publication Year: 2005,Page(s):26 – 33 vol. 2 Cited by: Papers (157) | Patents (9)
- Discriminative learning of Markov random fields for segmentation of 3D scan data D. Anguelov;B. Taskarf;V. Chatalbashev;D. Koller;D. Gupta;G. Heitz;A. Ng Publication Year: 2005,Page(s):169 – 176 vol. 2 Cited by: Papers (151) | Patents (8) )
- Damped Newton algorithms for matrix factorization with missing data A.M. Buchanan;A.W. Fitzgibbon Publication Year: 2005,Page(s):316 – 322 vol. 2 Cited by: Papers (145) | Patents (9)
- Multi-view stereo via volumetric graph-cuts G. Vogiatzis;P.H.S. Torr;R. Cipolla Publication Year: 2005,Page(s):391 – 398 vol. 2 Cited by: Papers (131) | Patents (5)
- Stereo correspondence by dynamic programming on a tree O. Veksler Publication Year: 2005,Page(s):384 – 390 vol. 2 Cited by: Papers (129) | Patents (2)
- Symmetric stereo matching for occlusion handling Jian Sun;Yin Li;S.B. Kang;Heung-Yeung Shum Publication Year: 2005,Page(s):399 – 406 vol. 2 Cited by: Papers (126) | Patents (11)
- Learning and detecting activities from movement trajectories using the hierarchical hidden Markov model N.T. Nguyen;D.Q. Phung;S. Venkatesh;H. Bui Publication Year: 2005,Page(s):955 – 960 vol. 2 Cited by: Papers (122) | Patents (1)
- Estimating 3D shape and texture using pixel intensity, edges, specular highlights, texture constraints and a prior S. Romdhani;T. Vetter Publication Year: 2005,Page(s):986 – 993 vol. 2 Cited by: Papers (117) | Patents (7)
- Level set based shape prior segmentation T. Chan;Wei Zhu Publication Year: 2005,Page(s):1164 – 1170 vol. 2 Cited by: Papers (107) | Patents (1)
- Local discriminant embedding and its variants Hwann-Tzong Chen;Huang-Wei Chang;Tyng-Luh Liu Publication Year: 2005,Page(s):846 – 853 vol. 2 Cited by: Papers (101) | Patents (4)
- Face recognition based on frontal views generated from non-frontal images V. Blanz;P. Grother;P.J. Phillips;T. Vetter Publication Year: 2005,Page(s):454 – 461 vol. 2 Cited by: Papers (96)
- WaldBoost – learning for time constrained sequential detection J. Sochman;J. Matas Publication Year: 2005,Page(s):150 – 156 vol. 2 Cited by: Papers (87) | Patents (4)
- Beyond pairwise clustering S. Agarwal;Jongwoo Lim;L. Zelnik-Manor;P. Perona;D. Kriegman;S. Belongie Publication Year: 2005,Page(s):838 – 845 vol. 2 Cited by: Papers (85)
https://ieeexplore.ieee.org/xpl/conhome/9901/proceeding?sortType=paper-citations