Depth from Defocus via Active Quasi-random Point Projections: A Deep Learning Approach

Autor:	David A. Clausi, Avery Ma, Alexander Wong
Rok vydání:	2017
Předmět:	Computer science business.industry Deep learning 3D reconstruction Convolutional neural network law.invention Computer graphics Projector law Measured depth Point (geometry) Computer vision Artificial intelligence Projection (set theory) business
Zdroj:	Lecture Notes in Computer Science ISBN: 9783319598758 ICIAR
Popis:	Depth estimation plays an important role in many computer vision and computer graphics applications. Existing depth measurement techniques are still complex and restrictive. In this paper, we present a novel technique for inferring depth measurements via depth from defocus using active quasi-random point projection patterns. A quasi-random point projection pattern is projected onto the scene of interest, and each projection point in the image captured by a cellphone camera is analyzed using a deep learning model to estimate the depth at that point. The proposed method has a relatively simple setup, consisting of a camera and a projector, and enables depth inference from a single capture. We evaluate the proposed method both quantitatively and qualitatively and demonstrate strong potential for simple and efficient depth sensing.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::6852d57e456aec53443e39fd20f50bfd https://doi.org/10.1007/978-3-319-59876-5_5 Zobrazit plný text záznamu