Deep Multi-Scale Feature Learning for Defocus Blur Estimation

TL;DR

This paper introduces a deep learning-based method for estimating defocus blur from a single image by classifying edges and interpolating blur maps, effectively preserving object boundaries and outperforming existing methods.

Contribution

It proposes a novel edge-based approach using CNNs to distinguish depth edges from pattern edges and accurately estimate blur, improving over prior techniques.

Findings

Outperforms state-of-the-art methods in qualitative and quantitative metrics

Effectively preserves object boundaries in dense blur maps

Achieves a good balance between accuracy and computational efficiency

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.