CVIVSep 10, 2020

HSolo: Homography from a single affine aware correspondence

arXiv:2009.05004v1
Originality Highly original
AI Analysis

This addresses the challenge of homography estimation in computer vision for applications like image stitching or object recognition where feature correspondences are often noisy, representing a novel method for a known bottleneck.

The paper tackles the problem of robust homography estimation in scenarios with low inlier rates by proposing a method that uses scale and rotation information from affine-aware feature detectors to estimate homography from a single correspondence, enabling effective filtering to improve performance, especially at low inlier rates.

The performance of existing robust homography estimation algorithms is highly dependent on the inlier rate of feature point correspondences. In this paper, we present a novel procedure for homography estimation that is particularly well suited for inlier-poor domains. By utilizing the scale and rotation byproducts created by affine aware feature detectors such as SIFT and SURF, we obtain an initial homography estimate from a single correspondence pair. This estimate allows us to filter the correspondences to an inlier-rich subset for use with a robust estimator. Especially at low inlier rates, our novel algorithm provides dramatic performance improvements.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes