At SIGGRAPH Asia, researchers from Carnegie Mellon’s CS department are demonstrating an interesting new algorithm capable of matching not only similar images, but matching paintings and sketches against databases of images looking for matches.
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.
Impressive stuff, check out their demo video below.
via Data-driven Visual Similarity for Cross-domain Image Matching.
