Name
Abstract | ||
|---|---|---|
Markov Random Field (MRF) models are a popular tool for vision and image processing. Gaussian MRF models are particularly convenient to work with because they can be implemented using matrix and linear algebra routines. However, recent research has focused on on discrete-valued and non-convex MRF models because Gaussian models tend to over-smooth images and blur edges. In this paper, we show how to train a Gaussian Conditional Random Field (GCRF) model that overcomes this weakness and can outperform the non-convex Field of Experts model on the task of denoising images. A key advantage of the GCRF model is that the parameters of the model can be optimized efficiently on relatively large images. The competitive performance of the GCRF model and the ease of optimizing its parameters make the GCRF model an attractive option for vision and image processing applications. |
Year | DOI | Venue |
|---|---|---|
2007 | 10.1109/CVPR.2007.382979 | 2007 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, VOLS 1-8 |
Keywords | Field | DocType |
markov processes,random processes,linear algebra,image reconstruction,edge detection,gaussian processes,conditional random field,computer vision,image processing,anisotropic magnetoresistance,design optimization,matrices,signal generators | Conditional random field,Computer vision,Linear algebra,Markov process,Pattern recognition,Edge detection,Markov random field,Computer science,Image processing,Gaussian,Gaussian process,Artificial intelligence | Conference |
Volume | Issue | ISSN |
2007 | 1 | 1063-6919 |
Citations | PageRank | References |
65 | 2.60 | 18 |
Authors | ||
4 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Marshall F. Tappen | 1 | 1901 | 89.34 |
| Ce Liu | 2 | 3347 | 188.04 |
| Edward H. Adelson | 3 | 1768 | 320.52 |
| William T. Freeman | 4 | 17382 | 1968.76 |