A Detector-oblivious Multi-arm Network for Keypoint Matching
This work addresses keypoint matching for computer vision applications, offering a detector-oblivious solution that avoids re-training for different detectors, though it appears incremental in its approach.
The paper tackles the problem of keypoint matching between images by proposing a Multi-Arm Network that learns region overlap and depth, improving robustness with minimal computational cost during inference. It outperforms state-of-the-art methods on outdoor and indoor datasets, as demonstrated in comprehensive experiments.
This paper presents a matching network to establish point correspondence between images. We propose a Multi-Arm Network (MAN) to learn region overlap and depth, which can greatly improve the keypoint matching robustness while bringing little computational cost during the inference stage. Another design that makes this framework different from many existing learning based pipelines that require re-training when a different keypoint detector is adopted, our network can directly work with different keypoint detectors without such a time-consuming re-training process. Comprehensive experiments conducted on outdoor and indoor datasets demonstrated that our proposed MAN outperforms state-of-the-art methods.