Low-rank SIFT: An Affine Invariant Feature for Place Recognition

TL;DR

This paper introduces Low-rank SIFT, a novel affine-invariant feature for place recognition that normalizes local patches to standard low-rank forms, enabling full affine invariance without simulating over affine parameters.

Contribution

The paper presents Low-rank SIFT, a new affine-invariant feature that normalizes local patches directly, improving place recognition and addressing affine parameter estimation challenges.

Findings

Achieves full affine invariance without simulating affine space

Effective in place recognition tasks

Efficient computation using convex optimization

Abstract

In this paper, we present a novel affine-invariant feature based on SIFT, leveraging the regular appearance of man-made objects. The feature achieves full affine invariance without needing to simulate over affine parameter space. Low-rank SIFT, as we name the feature, is based on our observation that local tilt, which are caused by changes of camera axis orientation, could be normalized by converting local patches to standard low-rank forms. Rotation, translation and scaling invariance could be achieved in ways similar to SIFT. As an extension of SIFT, our method seeks to add prior to solve the ill-posed affine parameter estimation problem and normalizes them directly, and is applicable to objects with regular structures. Furthermore, owing to recent breakthrough in convex optimization, such parameter could be computed efficiently. We will demonstrate its effectiveness in place recognition as our major application. As extra contributions, we also describe our pipeline of constructing geotagged building database from the ground up, as well as an efficient scheme for automatic feature selection.