Carnegie Mellon University
Browse

Data-driven Visual Similarity for Cross-domain Image Matching

Download (38.41 MB)
journal contribution
posted on 2018-06-30, 01:15 authored by Abhinav Shrivastava, Tomasz Malisiewicz, Abhinav GuptaAbhinav Gupta, Alexei Efros

The goal of this work is to find visually similar images even if they appear quite different at the raw pixel level. This task is particularly important for matching images across visual domains, such as photos taken over different seasons or lighting conditions, paintings, hand-drawn sketches, etc. We propose a surprisingly simple method that estimates the relative importance of different features in a query image based on the notion of "data-driven uniqueness". We employ standard tools from discriminative object detection in a novel way, yielding a generic approach that does not depend on a particular image representation or a specific visual domain. Our approach shows good performance on a number of difficult cross-domain visual tasks e.g., matching paintings or sketches to real photographs. The method also allows us to demonstrate novel applications such as Internet re-photography, and painting2gps.

History

Publisher Statement

© ACM, 2011. This is the author's version of the work.

Usage metrics

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC