One-Shot General Object Localization
This work addresses the challenge of generalizing one-shot localization to novel objects, which is important for applications like robotics and augmented reality, though it appears incremental in improving efficiency and accuracy.
The paper tackles the problem of one-shot object localization by proposing OneLoc, an algorithm that efficiently finds object centers and bounding boxes using a voting scheme, achieving state-of-the-art performance on the OnePose and LINEMOD datasets.
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.