Знайдено документів: 1
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

Матеріали
Препринт
Learning Discriminative Context-Aware Keypoints Representations for Resolving Ambiguous Matches
Viniavskyi Ostap. Learning Discriminative Context-Aware Keypoints Representations for Resolving Ambiguous Matches : публікація 2021-01-01; Український католицький університет, 2121U003118
Знайдено документів: 1

Оновлено: 2025-05-26


Роздрукувати цю сторінку