Virtual View Networks for Object Reconstruction

Joao Carreira, Abhishek Kar, Shubham Tulsiani, Jitendra Malik; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015, pp. 2937-2946

Abstract


All that structure from motion algorithms "see" are sets of 2D points. We show that these impoverished views of the world can be faked for the purpose of reconstructing objects in challenging settings, such as from a single image, or from a few ones far apart, by recognizing the object and getting help from a collection of images of other objects from the same class. We synthesize virtual views by computing geodesics on novel networks connecting objects with similar viewpoints, and introduce techniques to increase the specificity and robustness of factorization-based object reconstruction in this setting. We report accurate object shape reconstruction from a single image on challenging PASCAL VOC data, which suggests that the current domain of applications of rigid structure-from-motion techniques may be significantly extended.

Related Material


[pdf]
[bibtex]
@InProceedings{Carreira_2015_CVPR,
author = {Carreira, Joao and Kar, Abhishek and Tulsiani, Shubham and Malik, Jitendra},
title = {Virtual View Networks for Object Reconstruction},
booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2015}
}