Combining Monocular Geometric Cues with Traditional Stereo Cues for Consumer Camera Stereo
People
Adarsh Kowdle, Andrew Gallagher and Tsuhan Chen
Abstract
This paper presents an algorithm for considering both stereo cues and structural priors to obtain a geometrically representative depth map from a narrow baseline stereo pair. We use stereo pairs captured with a consumer stereo camera and observe that traditional depth estimation using stereo matching techniques encounters difficulties related to the narrow baseline relative to the depth of the scene. However, monocular geometric cues based on attributes such as lines and the horizon provide additional hints about the global structure that stereo matching misses. We merge both monocular and stereo matching features in a piecewise planar reconstruction framework that is initialized with a discrete inference step, and refined with a continuous optimization to encourage the intersections of hypothesized planes to coincide with observed image lines. We show through our results on stereo pairs of manmade structures captured outside of the lab that our algorithm exploits the advantages of both approaches to infer a better depth map of the scene.
Figure: Results using our proposed algorithm. Please refer to the paper for details.
Publications
- Adarsh Kowdle, Andrew Gallagher and Tsuhan Chen. "Combining Monocular Geometric Cues with Traditional Stereo Cues for Consumer Camera Stereo", Workshop on Unsolved Problems in Optical Flow and Stereo Estimation, European Conference on Computer Vision (ECCV), 2012. [pdf]
Dataset
We make the stereo pairs captures from our consumer stereo camera available here. These are image pairs captured using a Fujifilm FinePix 3D W1 camera. The raw .MPO files are included in the zip file. You can also view the pairs directly in the pdf. [Cornell ConsumerCamStereo Dataset | pdf].
If you use the 'Cornell ConsumerCamStereo Dataset' in your research, please cite the following paper,
- Adarsh Kowdle, Andrew Gallagher and Tsuhan Chen. "Combining Monocular Geometric Cues with Traditional Stereo Cues for Consumer Camera Stereo", Workshop on Unsolved Problems in Optical Flow and Stereo Estimation, European Conference on Computer Vision (ECCV), 2012.