Deep Multi-Scale Feature Learning for Defocus Blur Estimation

09/24/2020
by   Ali Karaali, et al.
14

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.

READ FULL TEXT

page 3

page 4

page 6

page 7

page 8

research
06/05/2020

MSDU-net: A Multi-Scale Dilated U-net for Blur Detection

Blur detection is the separation of blurred and clear regions of an imag...
research
11/17/2018

Edge-Based Blur Kernel Estimation Using Sparse Representation and Self-Similarity

Blind image deconvolution is the problem of recovering the latent image ...
research
05/10/2019

SABER: A Systems Approach to Blur Estimation and Reduction in X-ray Imaging

Blur in X-ray radiographs not only reduces the sharpness of image edges ...
research
06/20/2023

Depth and DOF Cues Make A Better Defocus Blur Detector

Defocus blur detection (DBD) separates in-focus and out-of-focus regions...
research
07/30/2021

Single image deep defocus estimation and its applications

The depth information is useful in many image processing applications. H...
research
11/30/2022

Gradient Domain Weighted Guided Image Filtering

As an excellent local filter, guided image filters are subject to halo a...
research
11/17/2019

Dense Color Constancy with Effective Edge Augmentation

Recently, computational color constancy via convolutional neural network...

Please sign up or login with your details

Forgot password? Click here to reset