An efficient algorithm for video superresolution based on a sequential model
From MaRDI portal
Image analysis in multivariate analysis (62H35) Ill-posedness and regularization problems in numerical linear algebra (65F22) Numerical optimization and variational techniques (65K10) Machine vision and scene understanding (68T45) Large-scale problems in mathematical programming (90C06) Nonconvex programming, global optimization (90C26)
Abstract: In this work, we propose a novel procedure for video super-resolution, that is the recovery of a sequence of high-resolution images from its low-resolution counterpart. Our approach is based on a "sequential" model (i.e., each high-resolution frame is supposed to be a displaced version of the preceding one) and considers the use of sparsity-enforcing priors. Both the recovery of the high-resolution images and the motion fields relating them is tackled. This leads to a large-dimensional, non-convex and non-smooth problem. We propose an algorithmic framework to address the latter. Our approach relies on fast gradient evaluation methods and modern optimization techniques for non-differentiable/non-convex problems. Unlike some other previous works, we show that there exists a provably-convergent method with a complexity linear in the problem dimensions. We assess the proposed optimization method on {several video benchmarks and emphasize its good performance with respect to the state of the art.}
Recommendations
Cites work
- A mathematical introduction to compressive sensing
- A Statistical Prediction Model Based on Sparse Representations for Single Image Super-Resolution
- A theoretical framework for convex regularizers in PDE-based computation of image motion
- A wavelet tour of signal processing. The sparse way.
- Convergence of descent methods for semi-algebraic and tame problems: proximal algorithms, forward-backward splitting, and regularized Gauss-Seidel methods
- Distributed optimization and statistical learning via the alternating direction method of multipliers
- Fast Discrete Curvelet Transforms
- scientific article; zbMATH DE number 1818892 (Why is no real title available?)
- scientific article; zbMATH DE number 2045491 (Why is no real title available?)
- scientific article; zbMATH DE number 804575 (Why is no real title available?)
- Image Super-Resolution Via Sparse Representation
- New tight frames of curvelets and optimal representations of objects with piecewise C2 singularities
- Nonlocally Centralized Sparse Representation for Image Restoration
- Nonorthogonal multiresolution analyses, commutation between projectors and differentiation and divergence-free vector wavelets
- Numerical Optimization
- On the Douglas-Rachford splitting method and the proximal point algorithm for maximal monotone operators
- Proximal Alternating Minimization and Projection Methods for Nonconvex Problems: An Approach Based on the Kurdyka-Łojasiewicz Inequality
- Registration Errors: Are They Always Bad for Super-Resolution?
- Robust image reconstruction from multiview measurements
- Statistical Analysis of the LMS Algorithm Applied to Super-Resolution Image Reconstruction
- Super Resolution Image Reconstruction Through Bregman Iteration Using Morphologic Regularization
- Super-resolution in diffraction tomography
- Super-Resolution Without Explicit Subpixel Motion Estimation
- Video Super-Resolution Using Simultaneous Motion and Intensity Calculations
Cited in
(16)- A state-space super-resolution approach for video reconstruction
- Reduced modeling of unknown trajectories
- Video superresolution via parameter-optimized particle swarm optimization
- A framelet algorithm for enhancing video stills
- Region-based super-resolution for compression
- A framelet-based algorithm for video enhancement
- Resolution enhancement of monochrome and color video using motion compensation
- scientific article; zbMATH DE number 2045501 (Why is no real title available?)
- Informed Choice of the LMS Parameters in Super-Resolution Video Reconstruction Applications
- scientific article; zbMATH DE number 1848293 (Why is no real title available?)
- Wavelet-based super resolution of downsampling-based compressed video
- Optimal operator space pursuit: a framework for video sequence data analysis
- Video super-resolution reconstruction based on spatio-temporal non-local similarity
- Local object-based super-resolution mosaicing from low-resolution video
- Chilled sampling for uncertainty quantification: a motivation from a meteorological inverse problem *
- Ordinal regression based subpixel shift estimation for video super-resolution
This page was built for publication: An efficient algorithm for video superresolution based on a sequential model
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3188197)
