A Learned Joint Depth and Intensity Prior Using Markov Random Fields

Author

Herrera, C. Daniel ; Kannala, Juho ; Sturm, Peter ; Heikkila, Janne

Author_Institution

Center for Machine Vision Res., Univ. of Oulu, Oulu, Finland

fYear

2013

fDate

June 29 2013-July 1 2013

Firstpage

17

Lastpage

24

Abstract

We present a joint prior that takes intensity and depth information into account. The prior is defined using a flexible Field-of-Experts model and is learned from a database of natural images. It is a generative model and has an efficient method for sampling. We use sampling from the model to perform in painting and up sampling of depth maps when intensity information is available. We show that including the intensity information in the prior improves the results obtained from the model. We also compare to another two-channel inpainting approach and show superior results.

Keywords

Markov processes; image sampling; visual databases; Markov random fields; depth maps; depth prior; flexible field-of-experts model; generative model; intensity prior; joint prior; natural image database; two-channel inpainting approach; upsampling method; Color; Databases; Image color analysis; Image resolution; Joints; Three-dimensional displays; Training; Field of experts; Markov Random Field; depth map inpainting; joint prior;

fLanguage

English

Publisher

ieee

Conference_Titel

3D Vision - 3DV 2013, 2013 International Conference on

Conference_Location

Seattle, WA

Type

conf

DOI

10.1109/3DV.2013.11

Filename

6599050