Learning to Detect Good Keypoints to Match Non-Rigid Objects in RGB Images

TL;DR

This paper introduces a learned keypoint detection method optimized for non-rigid image matching, significantly improving accuracy over existing detectors and enhancing descriptor matching in real-world applications.

Contribution

A novel CNN-based keypoint detection framework trained with true correspondences and geometric transformations, outperforming state-of-the-art methods on non-rigid objects.

Findings

Outperforms state-of-the-art on non-rigid image matching by 20 p.p.

Improves descriptor matching performance when combined with existing descriptors.

Achieves competitive results in real-world object retrieval applications.

Abstract

We present a novel learned keypoint detection method designed to maximize the number of correct matches for the task of non-rigid image correspondence. Our training framework uses true correspondences, obtained by matching annotated image pairs with a predefined descriptor extractor, as a ground-truth to train a convolutional neural network (CNN). We optimize the model architecture by applying known geometric transformations to images as the supervisory signal. Experiments show that our method outperforms the state-of-the-art keypoint detector on real images of non-rigid objects by 20 p.p. on Mean Matching Accuracy and also improves the matching performance of several descriptors when coupled with our detection method. We also employ the proposed method in one challenging realworld application: object retrieval, where our detector exhibits performance on par with the best available keypoint detectors. The source code and trained model are publicly available at https://github.com/verlab/LearningToDetect SIBGRAPI 2022