BANet: Blur-aware Attention Networks for Dynamic Scene Deblurring

01/19/2021
by   Fu-Jen Tsai, et al.
10

Image motion blur usually results from moving objects or camera shakes. Such blur is generally directional and non-uniform. Previous research efforts attempt to solve non-uniform blur by using self-recurrent multi-scale or multi-patch architectures accompanying with self-attention. However, using self-recurrent frameworks typically leads to a longer inference time, while inter-pixel or inter-channel self-attention may cause excessive memory usage. This paper proposes blur-aware attention networks (BANet) that accomplish accurate and efficient deblurring via a single forward pass. Our BANet utilizes region-based self-attention with multi-kernel strip pooling to disentangle blur patterns of different degrees and with cascaded parallel dilated convolution to aggregate multi-scale content features. Extensive experimental results on the GoPro and HIDE benchmarks demonstrate that the proposed BANet performs favorably against the state-of-the-art in blurred image restoration and can provide deblurred results in realtime.

READ FULL TEXT

page 2

page 3

page 4

page 5

page 6

page 7

research
04/10/2022

Stripformer: Strip Transformer for Fast Image Deblurring

Images taken in dynamic scenes may contain unwanted motion blur, which s...
research
06/27/2021

Blind Non-Uniform Motion Deblurring using Atrous Spatial Pyramid Deformable Convolution and Deblurring-Reblurring Consistency

Many deep learning based methods are designed to remove non-uniform (spa...
research
08/19/2020

Blur-Attention: A boosting mechanism for non-uniform blurred image restoration

Dynamic scene deblurring is a challenging problem in computer vision. It...
research
03/25/2019

Spatially-Adaptive Residual Networks for Efficient Image and Video Deblurring

In this paper, we address the problem of dynamic scene deblurring in the...
research
01/15/2021

Non-uniform Motion Deblurring with Blurry Component Divided Guidance

Blind image deblurring is a fundamental and challenging computer vision ...
research
12/23/2016

Blind restoration for non-uniform aerial images using non-local Retinex model and shearlet-based higher-order regularization

Aerial images are often degraded by space-varying motion blur and simult...
research
01/01/2022

Adaptive Single Image Deblurring

This paper tackles the problem of dynamic scene deblurring. Although end...

Please sign up or login with your details

Forgot password? Click here to reset