Data-driven Visual Similarity for Cross-domain Image Matching
Computer Vision Central - Posted on December 10, 2011 at 1:16 pm.
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.
Scene Matching (38.2MB)
Scene Completion (16.2MB)
Painting Matching (13.7MB)
Sketch Matching (13MB)
Watch in HD!
Source code for the basic infrastructure used in this paper (Exemplar-SVM infrastructure for large-scale training using a cluster, fast detection, etc.) is available for download:
You can also directly navigate to the Exemplar-SVM Github project page, which has download instructions, a wiki, and additional starter-guides.
Code specific to the experiments of this paper will be released soon.