Double Refinement Network for Room Layout Estimation

Авторы: Ivan Kruzhilov, Mikhail Romanov, Dmitry Babichev, Anton Konushin
Сборник: Palaiahnakote S., Sanniti di Baja G., Wang L., Yan W. (eds) Pattern Recognition. ACPR 2019
Серия: Lecture Notes in Computer Science
Том: 12046
Год издания: 2019
Место издания: Springer
Первая страница: 557
Последняя страница: 568
DOI: 10.1007/978-3-030-41404-7_39
Аннотация: Layout estimation is a challenge of segmenting a cluttered room image into floor, walls and ceiling. We applied Double refinement network proved to be efficient in the depth estimation to generate heat maps for room key points and edges. Our method is the first not using encoder-decoder architecture for the room layout estimation. ResNet50 was utilized as a backbone for the network instead of VGG16 commonly used for the task, allowing the network to be more compact and faster. We designed a special layout score function and layout ranking algorithm for key points and edges output. Our method achieved the lowest pixel and corner errors on the LSUN data set. The input image resolution is 224*224.
Добавил в систему: Конушин Антон Сергеевич

	ИСТИНА	Войти в систему Регистрация
	ФНКЦ РР
	Главная Поиск Статистика О проекте Помощь

ИСТИНА