• Publications
  • Influence
Fast and robust multiframe super resolution
TLDR
This paper proposes an alternate approach using L/sub 1/ norm minimization and robust regularization based on a bilateral prior to deal with different data and noise models and demonstrates its superiority to other super-resolution methods.
Kernel Regression for Image Processing and Reconstruction
TLDR
This paper adapt and expand kernel regression ideas for use in image denoising, upscaling, interpolation, fusion, and more and establishes key relationships with some popular existing methods and shows how several of these algorithms are special cases of the proposed framework.
Static and space-time visual saliency detection by self-resemblance.
TLDR
A novel unified framework for both static and space-time saliency detection, which results in a saliency map where each pixel indicates the statistical likelihood of saliency of a feature matrix given its surrounding feature matrices.
NIMA: Neural Image Assessment
TLDR
The proposed approach relies on the success (and retraining) of proven, state-of-the-art deep object recognition networks and can be used to not only score images reliably and with high correlation to human perception, but also to assist with adaptation and optimization of photo editing/enhancement algorithms in a photographic pipeline.
Analysis versus synthesis in signal priors
TLDR
This paper describes two prior classes, analysis-based and synthesis-based, and shows that although when reducing to the complete and under-complete formulations the two become equivalent, in their more interesting overcomplete formulation the two types depart.
The Little Engine That Could: Regularization by Denoising (RED)
TLDR
This paper provides an alternative, more powerful, and more flexible framework for achieving Regularization by Denoising (RED): using the denoising engine in defining the regulariza...
Generalizing the Nonlocal-Means to Super-Resolution Reconstruction
TLDR
This paper shows how this denoising method is generalized to become a relatively simple super-resolution algorithm with no explicit motion estimation, and results show that the proposed method is very successful in providing super- resolution on general sequences.
Automatic Parameter Selection for Denoising Algorithms Using a No-Reference Measure of Image Content
  • Xiang Zhu, P. Milanfar
  • Mathematics, Computer Science
    IEEE Transactions on Image Processing
  • 1 December 2010
TLDR
A no-reference metric Q is proposed which is based upon singular value decomposition of local image gradient matrix, and provides a quantitative measure of true image content in the presence of noise and other disturbances, and is used to automatically and effectively set the parameters of two leading image denoising algorithms.
Fast and Robust Multi-Frame Super-Resolution
Abstract from http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.15.2875&rep=rep1&type=pdf In the last two decades, many papers have been published, proposing a variety of methods for
Advances and challenges in super‐resolution
TLDR
A detailed study of several very important aspects of Super‐Resolution, often ignored in the literature, are presented, and robustness, treatment of color, and dynamic operation modes are discussed.
...
1
2
3
4
5
...