Learning to Detect Good Keypoints to Match Non-Rigid Objects in RGB Images
This work addresses the challenge of non-rigid object matching in computer vision, which is incremental as it builds on existing keypoint detection and descriptor methods.
The paper tackles the problem of detecting keypoints for matching non-rigid objects in RGB images by introducing a learned keypoint detection method that uses true correspondences and geometric transformations for training, resulting in a 20 percentage point improvement in Mean Matching Accuracy over state-of-the-art methods and enhanced descriptor performance.
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