“Shrinkage Fields (image restoration)”的意思、由来-开放百科全书

词条

Shrinkage Fields (image restoration)

释义

Method
Performance
Advantages
Implementations
See also
References

Shrinkage fields is a random field-based machine learning technique that aims to perform high quality image restoration (denoising and deblurring) using low computational overhead.

Method

The restored image is predicted from a corrupted observation after training on a set of sample images .

A shrinkage (mapping) function is directly modeled as a linear combination of radial basis function kernels, where is the shared precision parameter, denotes the (equidistant) kernel positions, and M is the number of Gaussian kernels.

Because the shrinkage function is directly modeled, the optimization procedure is reduced to a single quadratic minimization per iteration, denoted as the prediction of a shrinkage field where denotes the discrete Fourier transform and is the 2D convolution with point spread function filter, is an optical transfer function defined as the discrete Fourier transform of , and is the complex conjugate of .

is learned as for each iteration with the initial case , this forms a cascade of Gaussian conditional random fields (or cascade of shrinkage fields (CSF)). Loss-minimization is used to learn the model parameters .

The learning objective function is defined as , where is a differentiable loss function which is greedily minimized using training data and .

Performance

Preliminary tests by the author suggest that RTF₅^[1] obtains slightly better denoising performance than , followed by , , , and BM3D.

BM3D denoising speed falls between that of and , RTF being an order of magnitude slower.

Advantages

Results are comparable to those obtained by BM3D (reference in state of the art denoising since its inception in 2007)
Minimal runtime compared to other high-performance methods (potentially applicable within embedded devices)
Parallelizable (e.g.: possible GPU implementation)
Predictability: runtime where is the number of pixels
Fast training even with CPU

Implementations

A reference implementation has been written in MATLAB and released under the BSD 2-Clause license: [https://github.com/uschmidt83/shrinkage-fields shrinkage-fields]

References

1. ^{{cite conference |url= |title= Regression Tree Fields – An Efficient, Non-parametric Approach to Image Labeling Problems |last1=Jancsary |first1= Jeremy|last2=Nowozin |first2= Sebastian |last3=Sharp|first3=Toby|last4=Rother|first4=Carsten |author= |author-link= |date=10 April 2012 |year= |conference= IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR) |conference-url= |editor= |others= |volume= |edition= |book-title= |publisher= IEEE Computer Society |archive-url= |archive-date= |location=Providence, RI, USA |pages= |format= |id= |isbn= |bibcode= |oclc= |doi=10.1109/CVPR.2012.6247950 |access-date= |quote= |ref= |postscript= |language= |page= |at= |trans-title= }}

{{cite conference |title =Shrinkage Fields for Effective Image Restoration |first1 =Uwe |last1 =Schmidt |first2 =Stefan |last2 =Roth |url =http://research.uweschmidt.org/pubs/cvpr14schmidt.pdf |year =2014 |conference =Computer Vision and Pattern Recognition (CVPR), 2014 IEEE Conference on |publisher =IEEE |isbn =978-1-4799-5118-5 | doi =10.1109/CVPR.2014.349 |location =Colombus, OH, USA}}

1 : Image noise reduction techniques

随便看

开放百科全书收录14589846条英语、德语、日语等多语种百科知识，基本涵盖了大多数领域的百科知识，是一部内容自由、开放的电子版国际百科全书。

Method

Performance

Advantages

Implementations

See also

References