Surface Stereo with Soft Segmentation
By Michael Bleyer, Carsten Rother, and Pushmeet Kohli
Abstract
This paper proposes a new stereo model which encodes the simple assumption that the scene is composed of a few, smooth surfaces. A key feature of our model is the surface-based representation, where each pixel is assigned to a 3D surface (planes or B-splines). This representation enables several important contributions: Firstly, we formulate a higher-order prior which states that pixels of similar appearance are likely to belong to the same 3D surface. This enables to incorporate the very popular color segmentation constraint in a soft and principled way. Secondly, we use a global MDL prior to penalize the number of surfaces. Thirdly, we are able to incorporate, in a simple way, a prior which favors low curvature surfaces. Fourthly, we improve the asymmetric occlusion model by disallowing pixels of the same surface to occlude each other. Finally, we use the known fusion move approach which enables a powerful optimization of our model, despite the infinite number of possible labelings (surfaces).
Reference
M. Bleyer, C. Rother, P. Kohli: "Surface Stereo with Soft Segmentation"; Poster: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2010. CVPR '10, San Francisco, USA; 06-13-2010 - 06-18-2010; in: "IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2010. CVPR '10", IEEE, (2010), ISBN: 978-1-4244-6984-0; 1 - 8.
Additional Information
Supplementary material available for download: PDF file, Video (DivX compression).
The paper has won the Best Presentation Price at the International Computer Vision Summer School (ICVSS) 2010 in Sicily. Presentation slides are available here: PDF file, PPTX file.
Downloads
ICVSS | 2.87 MB | PowerPoint 2007 presentation | Download |
Surface Stereo | 477 KB | PDF document | Download |
Surface Stereo 2 | 1020 KB | PDF document | Download |
Surface Stereo Video | 3.15 MB | AVI video | Download |
BibTeX
Click into the text area and press Ctrl+A/Ctrl+C or ⌘+A/⌘+C to copy the BibTeX into your clipboard… or download the BibTeX.