Connecting Missing Links: Object Discovery from Sparse Observations using 5 Million Product Images - Robotics Institute Carnegie Mellon University

Connecting Missing Links: Object Discovery from Sparse Observations using 5 Million Product Images

Hongwen Kang, Martial Hebert, Alexei A. Efros, and Takeo Kanade
Conference Paper, Proceedings of (ECCV) European Conference on Computer Vision, pp. 794 - 807, October, 2012

Abstract

Object discovery algorithms group together image regions that originate from the same object. This process is effective when the input collection of images contains a large number of densely sampled views of each object, thereby creating strong connections between nearby views. However, existing approaches are less effective when the input data only provide sparse coverage of object views.

We propose an approach for object discovery that addresses this problem. We collect a database of about 5 million product images that capture 1.2 million objects from multiple views. We represent each region in the input image by a “bag” of database object regions. We group input regions together if they share similar “bags of regions.” Our approach can correctly discover links between regions of the same object even if they are captured from dramatically different viewpoints. With the help from these added links, our proposed approach can robustly discover object instances even with sparse coverage of the viewpoints.

BibTeX

@conference{Kang-2012-7599,
author = {Hongwen Kang and Martial Hebert and Alexei A. Efros and Takeo Kanade},
title = {Connecting Missing Links: Object Discovery from Sparse Observations using 5 Million Product Images},
booktitle = {Proceedings of (ECCV) European Conference on Computer Vision},
year = {2012},
month = {October},
pages = {794 - 807},
keywords = {Object Discovery, Sparse Observations, Product Images},
}