Beyond Cartesian Representations for Local Descriptors
This addresses the challenge of scale sensitivity in local descriptor matching for computer vision applications, offering a novel approach that enhances performance in tasks like image matching and retrieval.
The paper tackles the problem of local patch descriptor matching across scales by proposing a log-polar sampling scheme for support regions, which improves representation by oversampling near points and undersampling distant areas, enabling deep networks to match descriptors across a wider range of scales and achieve state-of-the-art results on three datasets.
The dominant approach for learning local patch descriptors relies on small image regions whose scale must be properly estimated a priori by a keypoint detector. In other words, if two patches are not in correspondence, their descriptors will not match. A strategy often used to alleviate this problem is to "pool" the pixel-wise features over log-polar regions, rather than regularly spaced ones. By contrast, we propose to extract the "support region" directly with a log-polar sampling scheme. We show that this provides us with a better representation by simultaneously oversampling the immediate neighbourhood of the point and undersampling regions far away from it. We demonstrate that this representation is particularly amenable to learning descriptors with deep networks. Our models can match descriptors across a much wider range of scales than was possible before, and also leverage much larger support regions without suffering from occlusions. We report state-of-the-art results on three different datasets.