Analysis by synthesis: 3d object recognition by object reconstruction
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"
}