Using Multi-view Recognition and Meta-data Annotation to Guide a Robot's Attention
International Journal of Robotics Research
Make3D: depth perception from a single still image
AAAI'08 Proceedings of the 23rd national conference on Artificial intelligence - Volume 3
Shape-from-recognition: Recognition enables meta-data transfer
Computer Vision and Image Understanding
A 2-point algorithm for 3D reconstruction of horizontal lines from a single omni-directional image
Pattern Recognition Letters
Inferring 3D shapes and deformations from single views
ECCV'10 Proceedings of the 11th European conference on computer vision conference on Computer vision: Part III
Single and sparse view 3D reconstruction by learning shape priors
Computer Vision and Image Understanding
Line Localization from Single Catadioptric Images
International Journal of Computer Vision
ACM Transactions on Applied Perception (TAP)
Computer Assisted Relief Generation—A Survey
Computer Graphics Forum
Shapecollage: occlusion-aware, example-based shape interpretation
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part III
Depth extraction from video using non-parametric sampling
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part V
An object expression system using depth-maps
Multimedia Tools and Applications
Reconstructing shape from dictionaries of shading primitives
ACCV'12 Proceedings of the 11th Asian conference on Computer Vision - Volume Part IV
| Hi-index | 0.00 |
We present a novel solution to the problem of depth reconstruction from a single image. Single view 3D reconstruction is an ill-posed problem. We address this problem by using an example-based synthesis approach. Our method uses a database of objects from a single class (e.g. hands, human figures) containing example patches of feasible mappings from the appearance to the depth of each object. Given an image of a novel object, we combine the known depths of patches from similar objects to produce a plausible depth estimate. This is achieved by optimizing a global target function representing the likelihood of the candidate depth. We demonstrate how the variability of 3D shapes and their poses can be handled by updating the example database on-the-fly. In addition, we show how we can employ our method for the novel task of recovering an estimate for the occluded backside of the imaged objects. Finally, we present results on a variety of object classes and a range of imaging conditions.