A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms
International Journal of Computer Vision
ICPR '02 Proceedings of the 16 th International Conference on Pattern Recognition (ICPR'02) Volume 4 - Volume 4
Locally Adaptive Support-Weight Approach for Visual Correspondence Search
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 2 - Volume 02
Putting Objects in Perspective
International Journal of Computer Vision
Blocks world revisited: image understanding using qualitative geometry and mechanics
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part IV
Category independent object proposals
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part V
Fast cost-volume filtering for visual correspondence and beyond
CVPR '11 Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition
Object stereo -- Joint stereo matching and object segmentation
CVPR '11 Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition
Object Recognition by Sequential Figure-Ground Ranking
International Journal of Computer Vision
StereoCut: Consistent interactive object selection in stereo image pairs
ICCV '11 Proceedings of the 2011 International Conference on Computer Vision
Hi-index | 0.00 |
This work combines two active areas of research in computer vision: unsupervised object extraction from a single image, and depth estimation from a stereo image pair. A recent, successful trend in unsupervised object extraction is to exploit so-called "3D scene-consistency", that is enforcing that objects obey underlying physical constraints of the 3D scene, such as occupancy of 3D space and gravity of objects. Our main contribution is to introduce the concept of 3D scene-consistency into stereo matching. We show that this concept is beneficial for both tasks, object extraction and depth estimation. In particular, we demonstrate that our approach is able to create a large set of 3D scene-consistent object proposals, by varying e.g. the prior on the number of objects. After automatically ranking the proposals we show experimentally that our results are considerably closer to ground truth than state-of-the-art techniques which either use stereo or monocular images. We envision that our method will build the front-end of a future object recognition system for stereo images.