Proceedings Article | 22 February 2012
KEYWORDS: 3D image processing, Databases, Image filtering, Image fusion, 3D modeling, Video, Associative arrays, Image restoration, 3D video streaming, Cameras
The availability of 3D hardware has so far outpaced the production of 3D content. Although to date many
methods have been proposed to convert 2D images to 3D stereopairs, the most successful ones involve human
operators and, therefore, are time-consuming and costly, while the fully-automatic ones have not yet achieved
the same level of quality. This subpar performance is due to the fact that automatic methods usually rely on
assumptions about the captured 3D scene that are often violated in practice. In this paper, we explore a radically
different approach inspired by our work on saliency detection in images. Instead of relying on a deterministic
scene model for the input 2D image, we propose to "learn" the model from a large dictionary of stereopairs, such
as YouTube 3D. Our new approach is built upon a key observation and an assumption. The key observation is
that among millions of stereopairs available on-line, there likely exist many stereopairs whose 3D content matches
that of the 2D input (query). We assume that two stereopairs whose left images are photometrically similar
are likely to have similar disparity fields. Our approach first finds a number of on-line stereopairs whose left
image is a close photometric match to the 2D query and then extracts depth information from these stereopairs.
Since disparities for the selected stereopairs differ due to differences in underlying image content, level of noise,
distortions, etc., we combine them by using the median. We apply the resulting median disparity field to the 2D
query to obtain the corresponding right image, while handling occlusions and newly-exposed areas in the usual
way. We have applied our method in two scenarios. First, we used YouTube 3D videos in search of the most
similar frames. Then, we repeated the experiments on a small, but carefully-selected, dictionary of stereopairs
closely matching the query. This, to a degree, emulates the results one would expect from the use of an extremely
large 3D repository. While far from perfect, the presented results demonstrate that on-line repositories of 3D
content can be used for effective 2D-to-3D image conversion. With the continuously increasing amount of 3D data
on-line and with the rapidly growing computing power in the cloud, the proposed framework seems a promising
alternative to operator-assisted 2D-to-3D conversion.