Automatic Class-Specific 3D Reconstruction from a Single Image
Author(s)
Lozano-Perez, Tomas; Kaelbling, Leslie Pack; Chiu, Han-Pang![Thumbnail](/bitstream/handle/1721.1/44615/MIT-CSAIL-TR-2009-008.pdf.jpg?sequence=5&isAllowed=y)
DownloadMIT-CSAIL-TR-2009-008.pdf (1.535Mb)
Additional downloads
Other Contributors
Learning and Intelligent Systems
Advisor
Tomas Lozano-Perez
Metadata
Show full item recordAbstract
Our goal is to automatically reconstruct 3D objects from a single image, by using prior 3D shape models of classes. The shape models, defined as a collection of oriented primitive shapes centered at fixed 3D positions, can be learned from a few labeled images for each class. The 3D class model can then be used to estimate the 3D shape of an object instance, including occluded parts, from a single image. We provide a quantitative evaluation of the shape estimation process on real objects and demonstrate its usefulness in three applications: robot manipulation, object detection, and generating 3D 'pop-up' models from photos.
Date issued
2009-02-18Series/Report no.
MIT-CSAIL-TR-2009-008