Authors:
Shahrouz Yousefi
;
Farid Abedan Kondori
and
Haibo Li
Affiliation:
Umeå University, Sweden
Keyword(s):
3D Visualization, Monocular Image, MRF, Depth Map, Color Anaglyph.
Related
Ontology
Subjects/Areas/Topics:
Human-Machine Interface
;
Image and Video Processing, Compression and Segmentation
;
Multidimensional Signal Processing
;
Multimedia
;
Multimedia and Communications
;
Multimedia Devices
;
Multimedia Signal Processing
;
Multimedia Systems and Applications
;
Perceptual/Human Audiovisual System Modeling
;
Telecommunications
Abstract:
In this paper we consider the task of 3D photo visualization using a single monocular image. The main idea is to use single photos taken by capturing devices such as ordinary cameras, mobile phones, tablet PCs etc. and visualize them in 3D on normal displays. Supervised learning approach is hired to retrieve depth information from single images. This algorithm is based on the hierarchical multi-scale Markov Random Field (MRF) which models the depth based on the multi-scale global and local features and relation between them in a monocular image. Consequently, the estimated depth image is used to allocate the specified depth parameters for each pixel in the 3D map. Accordingly, the multi-level depth adjustments and coding for color anaglyphs is performed. Our system receives a single 2D image as input and provides a anaglyph coded 3D image in output. Depending on the coding technology the special low-cost anaglyph glasses for viewers will be used.