Deep Multi-Scale Feature Learning for Defocus Blur Estimation
- 6 January 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 31 (10577149) , 1097-1106
Abstract
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.Keywords
All Related Versions
Funding Information
- ADAPT Centre for Digital Content Technology through the SFI Research Centres Programme (13/RC/2016)
- European Regional Development Fund
- Brazilian agencies Coordination for the Improvement of Higher Education Personnel (001)
- Brazilian National Council for Scientific and Technological Development
This publication has 36 references indexed in Scilit:
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015
- Discriminative Blur Detection Features2014
- Fast high-quality non-blind deconvolution using sparse adaptive priorsThe Visual Computer, 2014
- Salient Region Detection by UFO: Uniqueness, Focusness and Objectness2013
- Hierarchical Saliency Detection2013
- Defocus map estimation from a single imagePattern Recognition, 2011
- Domain transform for edge-aware image and video processingACM Transactions on Graphics, 2011
- Real-time lens blur effects and focus controlACM Transactions on Graphics, 2010
- Image and depth from a conventional camera with a coded apertureACM Transactions on Graphics, 2007
- Local scale control for edge detection and blur estimationIEEE Transactions on Pattern Analysis and Machine Intelligence, 1998