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

  • Welerson Melo UFMG
  • Guilherme Potje UFMG
  • Felipe Cadar UFMG
  • Renato Martins Université Bourgogne Franche-Comté
  • Erickson R. Nascimento UFMG

Resumo


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 real-world 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

Palavras-chave: Training, Graphics, Deformable models, Source coding, Pipelines, Detectors, Convolutional neural networks
Publicado
24/10/2022
MELO, Welerson; POTJE, Guilherme; CADAR, Felipe; MARTINS, Renato; NASCIMENTO, Erickson R.. Learning to Detect Good Keypoints to Match Non-Rigid Objects in RGB Images. In: CONFERENCE ON GRAPHICS, PATTERNS AND IMAGES (SIBGRAPI), 35. , 2022, Natal/RN. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2022 .