 |
    |
Connecting Missing Links: Object Discovery from Sparse Observations Using 5 Million Product Images
Hongwen Kang, Martial Hebert, Alexei A. Efros, and Takeo Kanade
School of Computer Science, Carnegie Mellon University, USAhongwenk@cs.cmu.edu
hebert@cs.cmu.edu
efros@cs.cmu.edu
tk@cs.cmu.edu
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.
LNCS 7577, p. 794 ff.
lncs@springer.com
© Springer-Verlag Berlin Heidelberg 2012