Abstract | ||
---|---|---|
Many computer vision problems can be formulated in a Bayesian framework based on Markov random fields (MRF) or conditional random fields (CRF). Generally, the MRF/CRF model is learned independently of the inference algorithm that is used to obtain the final result. In this paper, we observe considerable gains in speed and accuracy by training the MRF/CRF model together with a fast and suboptimal inference algorithm. An active random field (ARF) is defined as a combination of a MRF/CRF based model and a fast inference algorithm for the MRF/CRF model. This combination is trained through an optimization of a loss function and a training set consisting of pairs of input images and desired outputs. We apply the ARF concept to image denoising, using the Fields of Experts MRF together with a 1-4 iteration gradient descent algorithm for inference. Experimental validation on unseen data shows that the ARF approach obtains an improved benchmark performance as well as a 1000-3000 times speedup compared to the Fields of Experts MRF. Using the ARF approach, image denoising can be performed in real-time, at 8fps on a single CPU for a 256 x 256 image sequence, with close to state-of-the-art accuracy. |
Year | DOI | Venue |
---|---|---|
2009 | 10.1109/TIP.2009.2028254 | IEEE Transactions on Image Processing |
Keywords | Field | DocType |
real-time image denoising,crf model,fast inference algorithm,active random field,arf concept,image denoising,suboptimal inference algorithm,inference algorithm,markov random field,arf approach,iteration gradient descent algorithm,experts mrf,gradient descent,real time,computer vision,polynomials,markov processes,random field,indexing terms,bayesian methods,conditional random fields,conditional random field,mathematical model,application software,loss function | Conditional random field,Gradient method,Gradient descent,Random field,Pattern recognition,Inference,Markov model,Markov chain,Image processing,Artificial intelligence,Mathematics | Journal |
Volume | Issue | ISSN |
18 | 11 | 1941-0042 |
Citations | PageRank | References |
36 | 1.95 | 39 |
Authors | ||
1 |
Name | Order | Citations | PageRank |
---|---|---|---|
Adrian Barbu | 1 | 768 | 58.59 |