Deep Multi-Scale Feature Learning for Defocus Blur Estimation

Autor:	Karaali, Ali, Harte, Naomi, Jung, Claudio Rosito
Rok vydání:	2020
Předmět:	Computer Science - Computer Vision and Pattern Recognition Computer Science - Machine Learning Computer Science - Multimedia
Druh dokumentu:	Working Paper
Popis:	This paper presents an edge-based defocus blur estimation method from a single defocused image. We first distinguish edges that lie at depth discontinuities (called depth edges, for which the blur estimate is ambiguous) from edges that lie at approximately constant depth regions (called pattern edges, for which the blur estimate is well-defined). Then, we estimate the defocus blur amount at pattern edges only, and explore an interpolation scheme based on guided filters that prevents data propagation across the detected depth edges to obtain a dense blur map with well-defined object boundaries. Both tasks (edge classification and blur estimation) are performed by deep convolutional neural networks (CNNs) that share weights to learn meaningful local features from multi-scale patches centered at edge locations. Experiments on naturally defocused images show that the proposed method presents qualitative and quantitative results that outperform state-of-the-art (SOTA) methods, with a good compromise between running time and accuracy. Comment: under review
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2009.11939 Zobrazit plný text záznamu View this record from Arxiv