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

Abstract

Blur detection is the separation of blurred and clear regions of an image, which is an important and challenging task in computer vision. In this work, we regard blur detection as an image segmentation problem. Inspired by the success of the U-net architecture for image segmentation, we design a Multi-Scale Dilated convolutional neural network based on U-net, which we call MSDU-net. The MSDU-net uses a group of multi-scale feature extractors with dilated convolutions to extract texture information at different scales. The U-shape architecture of the MSDU-net fuses the different-scale texture features and generates a semantic feature which allows us to achieve better results on the blur detection task. We show that using the MSDU-net we are able to outperform other state of the art blur detection methods on two publicly available benchmarks.

References in corpus (10)

• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
• Rethinking Atrous Convolution for Semantic Image Segmentation
• YOLOv3: An Incremental Improvement
• Attention U-Net: Learning Where to Look for the Pancreas
• Deep Convolutional Neural Network for Inverse Problems in Imaging
• ResUNet-a: a deep learning framework for semantic segmentation of remotely sensed data
• ParseNet: Looking Wider to See Better
• TernausNet: U-Net with VGG11 Encoder Pre-Trained on ImageNet for Image Segmentation
• Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution