Пошук академічних текстів

Інформація × Реєстраційний номер 2121U003118, Матеріали видань та локальних репозитаріїв Категорія Препринт Назва роботи Learning Discriminative Context-Aware Keypoints Representations for Resolving Ambiguous Matches Автор Viniavskyi Ostap Дата публікації 01-01-2021 Постачальник інформації Український католицький університет Першоджерело https://hdl.handle.net/20.500.14570/2874 Видання Опис In the feature matching problem, local keypoint representations are often not sufficiently distinctive to disambiguate repetitive textures. State-of-the-art matching pipelines encode global information and embed context into keypoint descriptors to resolve this issue. In this thesis, we evaluate the failure modes of the state-ofthe- art method for image matching. We identify the problem that including global context to keypoint representations can sometimes eliminate their distinctiveness. We propose to enhance the learning of the state-of-the-art pipeline by adding a metric learning component to its objective function. By learning more distinctive global context-aware keypoint descriptors, we recover the filtered matches without the loss in matching precision. Додано в НРАТ 2025-05-09 Закрити