Data-Driven 3D Primitives for Single Image Understanding - Robotics Institute Carnegie Mellon University

Data-Driven 3D Primitives for Single Image Understanding

Conference Paper, Proceedings of (ICCV) International Conference on Computer Vision, pp. 3392 - 3399, December, 2013

Abstract

What primitives should we use to infer the rich 3D world behind an image? We argue that these primitives should be both visually discriminative and geometrically informative and we present a technique for discovering such primitives. We demonstrate the utility of our primitives by using them to infer 3D surface normals given a single image. Our technique substantially outperforms the state-of-the-art and shows improved cross-dataset performance.

BibTeX

@conference{Fouhey-2013-7799,
author = {David Fouhey and Abhinav Gupta and Martial Hebert},
title = {Data-Driven 3D Primitives for Single Image Understanding},
booktitle = {Proceedings of (ICCV) International Conference on Computer Vision},
year = {2013},
month = {December},
pages = {3392 - 3399},
}