Example Based 3D Reconstruction from Single 2D Images
Hassner, T.; Basri, R.
Computer Vision and Pattern Recognition Workshop, 2006. CVPRW apos;06. Conference on
Volume , Issue , 17-22 June 2006 Page(s): 15 - 15
Digital Object Identifier 10.1109/CVPRW.2006.76
Summary: 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.
View citation and abstract |
Cart
