Blocks world revisited: image understanding using qualitative geometry and mechanics
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part IV
Retrieving images of similar geometrical configuration
ISVC'10 Proceedings of the 6th international conference on Advances in visual computing - Volume Part II
Combining plane estimation with shape detection for holistic scene understanding
ACIVS'11 Proceedings of the 13th international conference on Advanced concepts for intelligent vision systems
Binocular stereopsis of traditional Chinese paintings
Proceedings of the 10th International Conference on Virtual Reality Continuum and Its Applications in Industry
The Visual Extent of an Object
International Journal of Computer Vision
Real-time estimation of 3D scene geometry from a single image
Pattern Recognition
Hi-index | 0.14 |
Reconstruction of 3D scene geometry is an important element for scene understanding, autonomous vehicle and robot navigation, image retrieval, and 3D television. We propose accounting for the inherent structure of the visual world when trying to solve the scene reconstruction problem. Consequently, we identify geometric scene categorization as the first step toward robust and efficient depth estimation from single images. We introduce 15 typical 3D scene geometries called stages, each with a unique depth profile, which roughly correspond to a large majority of broadcast video frames. Stage information serves as a first approximation of global depth, narrowing down the search space in depth estimation and object localization. We propose different sets of low-level features for depth estimation, and perform stage classification on two diverse data sets of television broadcasts. Classification results demonstrate that stages can often be efficiently learned from low-dimensional image representations.