Image Synthesis from a Single Example Image
Abstract
The need to generate new views of a 3D object from a single real image arises in several fields, including graphics and object recognition. While the traditional approach relies on the use of 3D models, we exploit 2D image transformations that are specific to the relevant object class and learnable from example views of other “prototypical” objects of the same class. For linear object classes we show that linear transformations can be learned exactly from a basis set of 2D prototypical views. We demonstrate the approach on artificial objects and then show preliminary evidence that the technique can effectively “rotate” high-resolution face images from a single 2D view.
Cite
Text
Vetter and Poggio. "Image Synthesis from a Single Example Image." European Conference on Computer Vision, 1996. doi:10.1007/BFB0015575Markdown
[Vetter and Poggio. "Image Synthesis from a Single Example Image." European Conference on Computer Vision, 1996.](https://mlanthology.org/eccv/1996/vetter1996eccv-image/) doi:10.1007/BFB0015575BibTeX
@inproceedings{vetter1996eccv-image,
title = {{Image Synthesis from a Single Example Image}},
author = {Vetter, Thomas and Poggio, Tomaso A.},
booktitle = {European Conference on Computer Vision},
year = {1996},
pages = {652-659},
doi = {10.1007/BFB0015575},
url = {https://mlanthology.org/eccv/1996/vetter1996eccv-image/}
}