Analysis by synthesis: 3d object recognition by object reconstruction
icon We introduce a new approach for recognizing and reconstructing 3D objects in images. Our approach is based on an analysis by synthesis strategy. A forward synthesis model constructs possible geometric interpretations of the world, and then selects the interpretation that best agrees with the measured visual evidence. The forward model synthesizes visual templates defined on invariant (HOG) features. These visual templates are discriminatively trained to be accurate for inverse estimation. We introduce an efficient “brute-force” approach to inference that searches through a large number of candidate reconstructions, returning the optimal one. One benefit of such an approach is that recognition is inherently (re)constructive. We show state of the art performance for detection and reconstruction on two challenging 3D object recognition datasets of cars and cuboids.

Download: pdf

Text Reference

Mohsen Hejrati and Deva Ramanan. Analysis by synthesis: 3d object recognition by object reconstruction. In Computer Vision and Pattern Recognition (CVPR), 2014 IEEE Conference on, 2449–2456. IEEE, 2014.

BibTeX Reference

@inproceedings{HejratiR_CVPR_2014,
    author = "Hejrati, Mohsen and Ramanan, Deva",
    title = "Analysis by synthesis: 3d object recognition by object reconstruction",
    booktitle = "Computer Vision and Pattern Recognition (CVPR), 2014 IEEE Conference on",
    pages = "2449--2456",
    year = "2014",
    organization = "IEEE",
    tag = "geometry"
}