Robust Semi-Automatic Depth Map Generation in Unconstrained Images and Video Sequences for 2D to Stereoscopic 3D Conversion

We describe a system for robustly estimating synthetic depth maps in unconstrained images and videos, for semi-automatic conversion into stereoscopic 3D. Currently, this process is automatic or done manually by rotoscopers. Automatic is the least labor intensive, but makes user intervention or error...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on multimedia 2014-01, Vol.16 (1), p.122-136
Main Authors: Phan, Raymond, Androutsos, Dimitrios
Format: Article
Language:English
Subjects:
2D to 3D image conversion
2D to 3D video conversion
Algorithmics. Computability. Computer arithmetics
Applied sciences
Artificial intelligence
Cameras
Computer science
control theory
systems
Computer vision
depth maps
Exact sciences and technology
graph cuts
Image color analysis
Image segmentation
Information retrieval. Graph
motion estimation
object tracking
Pattern recognition. Digital image processing. Computational geometry
random walks
semi-automatic
Stereo image processing
Support vector machines
Theoretical computing
Three-dimensional displays
Video sequences
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We describe a system for robustly estimating synthetic depth maps in unconstrained images and videos, for semi-automatic conversion into stereoscopic 3D. Currently, this process is automatic or done manually by rotoscopers. Automatic is the least labor intensive, but makes user intervention or error correction difficult. Manual is the most accurate, but time consuming and costly. Noting the merits of both, a semi-automatic method blends them together, allowing for faster and accurate conversion. This requires user-defined strokes on the image, or over several keyframes for video, corresponding to a rough estimate of the depths. After, the rest of the depths are determined, creating depth maps to generate stereoscopic 3D content, with Depth Image Based Rendering to generate the artificial views. Depth map estimation can be considered as a multi-label segmentation problem: each class is a depth. For video, we allow the user to label only the first frame, and we propagate the strokes using computer vision techniques. We combine the merits of two well-respected segmentation algorithms: Graph Cuts and Random Walks. The diffusion from Random Walks, with the edge preserving of Graph Cuts should give good results. We generate good quality content, more suitable for perception, compared to a similar framework.
ISSN:1520-9210
1941-0077
DOI:10.1109/TMM.2013.2283451