Super-resolution from image sequences-a review
Published 27 November 2002
Sean Borman, Robert Louis Stevenson
Citations351
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
The state of the art of SR techniques is reviewed using a taxonomy of existing techniques and areas which promise performance improvements are identified.
Abstract
Growing interest in super-resolution (SR) restoration of video sequences and the closed related problem of construction of SR still images from image sequences has led to the emergence of several competing methodologies. We review the state of the art of SR techniques using a taxonomy of existing techniques. We critique these methods and identified areas which promise performance improvements.
Keywords
Computer ScienceEngineering
IEEE Transactions on Image ProcessingRestoration of a single superresolution image from several blurred, noisy, and undersampled measured images
1,024 Citations1997Michael Elad, Arie Feuer
A hybrid method combining the simplicity of theML and the incorporation of nonellipsoid constraints is presented, giving improved restoration performance, compared with the ML and the POCS approaches.
IEEE Transactions on Image ProcessingExtraction of high-resolution frames from video sequences
968 Citations1996Richard R. Schultz, Robert Louis Stevenson
A novel observation model based on motion compensated subsampling is proposed for a video sequence and Bayesian restoration with a discontinuity-preserving prior image model is used to extract a high-resolution video still given a short low-resolution sequence.
IEEE Transactions on Image ProcessingJoint MAP registration and high-resolution image estimation using a sequence of undersampled images
819 Citations1997Russell C. Hardie, Kenneth J. Barnard +1 more
A maximum a posteriori (MAP) framework for jointly estimating image registration parameters and the high-resolution image is presented and experimental results are provided to illustrate the performance of the proposed MAP algorithm using both visible and infrared images.
Journal of Visual Communication and Image RepresentationMotion Analysis for Image Enhancement: Resolution, Occlusion, and Transparency
801 Citations1993Michal Irani, Shmuel Peleg
Accurate computation of image motion enables the enhancement of image sequences that include improvement of image resolution, filling-in occluded regions, and reconstruction of transparent objects.
IEEE Transactions on Acoustics Speech and Signal ProcessingRecursive reconstruction of high resolution image from noisy undersampled multiframes
515 Citations1990S.P. Kim, N.K. Bose +1 more
An algorithm based on weighted recursive least-squares theory is developed in the wavenumber domain, which is efficient because interpolation and noise removal are performed recursively, and is highly suitable for implementation via the massively parallel computational architectures currently available.
IEEE Transactions on Image ProcessingSuperresolution video reconstruction with arbitrary sampling lattices and nonzero aperture time
450 Citations1997A.J. Patti, M. Ibrahim Sezan +1 more
Experimental results with real video demonstrate that a significant increase in the image resolution can be achieved by taking the motion blurring into account especially when there exists large interframe motion.
High-resolution image reconstruction from lower-resolution image sequences and space-varying image restoration
309 Citations1992A. Murat Tekalp, M.K. Ozkan +1 more
CVGIP Graphical Models and Image ProcessingImproved resolution from subpixel shifted pictures
288 Citations1992Hanoch Ur, Daniel Groß
It is shown that the procedure achieves the claims of super resolution schemes but, unlike many of them, is well posed and robust.
IEEE Transactions on Image ProcessingRecursive high-resolution reconstruction of blurred multiframe images
250 Citations1993S.P. Kim, Wei Su
IEEE Transactions on Image ProcessingSuperresolution restoration of an image sequence: adaptive filtering approach
223 Citations1999Michael Elad, Arie Feuer
The proposed methodology suggests least squares estimators which adapt in time, based on adaptive filters, least mean squares (LMS) or recursive least squares (RLS), which enables the treatment of linear space and time-variant blurring and arbitrary motion.
Super-Resolved Surface Reconstruction from Multiple Images
209 Citations1996Peter Cheeseman, Bob Kanefsky +3 more
A Bayesian method for constructing a super-resolved surface model by combining information from a set of images of the given surface by using a neighbor correlation model as well as pixel data from the image set is described.
IEEE Transactions on Circuits and SystemsMulti-channel sampling of low-pass signals
200 Citations1981J. Brown
The system of equations derived here has the advantage of depending on only one parameter \omega rather than on the two parameters t, and puts into evidence the fact that the spectra of the optimal reconstruction filters can be pieced together directly, without additional computation, from the elements of the system's inverse matrix.
IEEE Transactions on Image ProcessingRobust, object-based high-resolution image reconstruction from low-resolution video
121 Citations1997P. Erhan Eren, M. Ibrahim Sezan +1 more
A robust, object-based approach to high-resolution image reconstruction from video using the projections onto convex sets (POCS) framework using a validity map and/or a segmentation map to improve the quality of the reconstructed image.
IEEE International Conference on Acoustics Speech and Signal ProcessingRecursive implementation of total least squares algorithm for image reconstruction from noisy, undersampled multiframes
91 Citations1993N.K. Bose, H.C. Kim +1 more
It is shown how the total least squares recursive algorithm for the real data FIR (finite impulse response) adaptive filtering problem can be applied to reconstruct a high-resolution filtered image from undersampled, noisy multiframes, when the interframe displacements are not accurately known.
Signal Processing Image CommunicationVery high resolution imaging scheme with multiple different-aperture cameras
72 Citations1993Takashi Komatsu, Toru Igarashi +2 more
This work presents the utilization of multiple cameras with different pixel apertures, and develops a new, alternately iterative signal processing algorithm available in the different aperture case, which performs satisfactorily in experimental simulations.
Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE<title>Reconstruction of a high-resolution image from multiple-degraded misregistered low-resolution images</title>
66 Citations1994Brian C. Tom, Aggelos K. Katsaggelos
Based on previous restoration and identification work using the Expectation-Maximization algorithm, the proposed approach estimates the sub-pixel shifts and conditional mean (restored images) simultaneously simultaneously and is cast in a multi-channel framework to take advantage of the cross- channel information.
Multidimensional Systems and Signal ProcessingRecursive total least squares algorithm for image reconstruction from noisy, undersampled frames
55 Citations1993N.K. Bose, H. C. Kim +1 more
It is shown how the efficient recursive total least squares algorithm recently developed by C.E. Davila for real data can be applied to image reconstruction from noisy, undersampled multiframes when the displacement of each frame relative to a reference frame is not accurately known.
IEEE Transactions on Image ProcessingA new motion-compensated reduced-order model Kalman filter for space-varying restoration of progressive and interlaced video
45 Citations1998A.J. Patti, A. Murat Tekalp +1 more
The proposed modeling, which includes the two-dimensional (2-D) reduced order model Kalman filtering (ROMKF) of Angwin and Kaufman as a special case, results in significant performance improvement in fixed-lag Kalman filters of space-varying blurred images.
Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE<title>Iterative algorithm for improving the resolution of video sequences</title>
38 Citations1996Brian C. Tom, Aggelos K. Katsaggelos
This paper introduces an iterative and temporally recursive technique to improve the spatial resolution of a video sequence by incorporating prior information into the restoration and the removal of the need for taking inverses of matrices.
Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE<title>Regularized multichannel restoration approach for globally optimal high-resolution video sequence</title>
38 Citations1997Min-Cheol Hong, Moon Gi Kang +1 more
A multiple input smoothing convex functional is defined and used to obtain a globally optimal high resolution video sequence by using the point spread function between the original and bilinearly interpolated images in the spatial domain, and motion estimation between frames in the temporal domain.
Multiframe spatial resolution enhancement of color video
14 Citations2002Nilima Shah, Avideh Zakhor
Enhanced frames using this technique show significant improvement in both SNR and perceived visual quality over methods such as bilinear and cubic B-spline interpolation.