Image Matching with Scale Adjustment
Yves Dufournaud, Cordelia Schmid, and Radu Horaud

TL;DR
This paper presents a novel method for matching images with different resolutions by utilizing scale-space representations, invariant descriptors, and geometric modeling, effectively handling scale differences up to a factor of 6.
Contribution
The paper introduces a new approach for matching images at different resolutions using scale-space analysis and invariant feature descriptors, addressing unknown resolution differences.
Findings
Effective for scale changes up to a factor of 6
Uses scale-space representation for interest point detection
Employs robust geometric model estimation
Abstract
In this paper we address the problem of matching two images with two different resolutions: a high-resolution image and a low-resolution one. The difference in resolution between the two images is not known and without loss of generality one of the images is assumed to be the high-resolution one. On the premise that changes in resolution act as a smoothing equivalent to changes in scale, a scale-space representation of the high-resolution image is produced. Hence the one-to-one classical image matching paradigm becomes one-to-many because the low-resolution image is compared with all the scale-space representations of the high-resolution one. Key to the success of such a process is the proper representation of the features to be matched in scale-space. We show how to represent and extract interest points at variable scales and we devise a method allowing the comparison of two images at…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
