Abstract | ||
---|---|---|
We present a generative, probabilistic model that decomposes an image into reflectance and shading components. The proposed approach uses a Dirichlet process Gaussian mixture model where the mean parameters evolve jointly according to a Gaussian process. In contrast to prior methods, we eliminate the Retinex term and adopt more general smoothness assumptions for the shading image. Markov chain Monte Carlo sampling techniques are used for inference, yielding state-of-the-art results on the MIT Intrinsic Image Dataset. |
Year | DOI | Venue |
---|---|---|
2014 | 10.1007/978-3-319-10593-2_46 | COMPUTER VISION - ECCV 2014, PT IV |
Keywords | Field | DocType |
Intrinsic images, Dirichlet process, Gaussian process, MCMC | Computer vision,Color constancy,Dirichlet process,Markov chain Monte Carlo,Inference,Computer science,Algorithm,Artificial intelligence,Statistical model,Gaussian process,Smoothness,Shading | Conference |
Volume | ISSN | Citations |
8692 | 0302-9743 | 4 |
PageRank | References | Authors |
0.86 | 9 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jason Chang | 1 | 133 | 6.75 |
Randi Cabezas | 2 | 4 | 0.86 |
John W. Fisher III | 3 | 878 | 74.44 |