Scale Assignment for Imbalanced Points

Abstract

Imbalance oriented candidate selection was introduced as an alternative of non-maximum suppression, aiming to improve the localization accuracy. To distinguish interest points detected via non-maximum suppression, we call interest points detected via imbalance oriented selection imbalanced points. Scale assignment for imbalanced points is not straightforward because of a dilemma of involving non-maximum suppression -- The scale space theory, a popular scale assignment scheme, requests non-maximum suppression to detect extreme points from scale spaces, while imbalanced points are expected to be free of non-maximum suppression in order to maintain the localization accuracy. In this paper, we propose a bypass scheme that circumvents the above dilemma by establishing an association between an imbalanced point and a certain interest point with a known scale (e.g., key points). We justify the proposed bypass scheme theoretically and experimentally. For example, our results show that epipolar geometry estimated via imbalanced points with bypass scales is more consistent with ground truth than key points.