@inproceedings{d05014877bf641768683fa8b080f040d,
title = "Learning a predictable and generative vector representation for objects",
abstract = "What is a good vector representation of an object? We believe that it should be generative in 3D, in the sense that it can produce new 3D objects; as well as be predictable from 2D, in the sense that it can be perceived from 2D images. We propose a novel architecture, called the TL-embedding network, to learn an embedding space with these properties. The network consists of two components: (a) an autoencoder that ensures the representation is generative; and (b) a convolutional network that ensures the representation is predictable. This enables tackling a number of tasks including voxel prediction from 2D images and 3D model retrieval. Extensive experimental analysis demonstrates the usefulness and versatility of this embedding.",
author = "Rohit Girdhar and Fouhey, {David F.} and Mikel Rodriguez and Abhinav Gupta",
note = "Publisher Copyright: {\textcopyright} Springer International Publishing AG 2016.; 14th European Conference on Computer Vision, ECCV 2016 ; Conference date: 08-10-2016 Through 16-10-2016",
year = "2016",
doi = "10.1007/978-3-319-46466-4_29",
language = "English (US)",
isbn = "9783319464657",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
publisher = "Springer Verlag",
pages = "484--499",
editor = "Bastian Leibe and Jiri Matas and Nicu Sebe and Max Welling",
booktitle = "Computer Vision - 14th European Conference, ECCV 2016, Proceedings",
}