One-Shot General Object Localization

TL;DR

This paper introduces OneLoc, a fast and scalable one-shot object localization algorithm that accurately finds object centers and sizes, outperforming previous methods on multiple datasets and supporting multi-instance and non-rigid object detection.

Contribution

The paper proposes a novel, efficient one-shot localization method with a dense voting scheme and scale-invariance, improving accuracy and generalization over existing approaches.

Findings

Achieves state-of-the-art performance on OnePose and LINEMOD datasets.

Supports one-shot multi-instance detection.

Effectively localizes non-rigid and texture-less objects.

Abstract

This paper presents a general one-shot object localization algorithm called OneLoc. Current one-shot object localization or detection methods either rely on a slow exhaustive feature matching process or lack the ability to generalize to novel objects. In contrast, our proposed OneLoc algorithm efficiently finds the object center and bounding box size by a special voting scheme. To keep our method scale-invariant, only unit center offset directions and relative sizes are estimated. A novel dense equalized voting module is proposed to better locate small texture-less objects. Experiments show that the proposed method achieves state-of-the-art overall performance on two datasets: OnePose dataset and LINEMOD dataset. In addition, our method can also achieve one-shot multi-instance detection and non-rigid object localization. Code repository: https://github.com/qq456cvb/OneLoc.