BaMBNet: A Blur-aware Multi-branch Network for Defocus Deblurring

05/31/2021
by   Pengwei Liang, et al.
3

The defocus deblurring raised from the finite aperture size and exposure time is an essential problem in the computational photography. It is very challenging because the blur kernel is spatially varying and difficult to estimate by traditional methods. Due to its great breakthrough in low-level tasks, convolutional neural networks (CNNs) have been introduced to the defocus deblurring problem and achieved significant progress. However, they apply the same kernel for different regions of the defocus blurred images, thus it is difficult to handle these nonuniform blurred images. To this end, this study designs a novel blur-aware multi-branch network (BaMBNet), in which different regions (with different blur amounts) should be treated differentially. In particular, we estimate the blur amounts of different regions by the internal geometric constraint of the DP data, which measures the defocus disparity between the left and right views. Based on the assumption that different image regions with different blur amounts have different deblurring difficulties, we leverage different networks with different capacities (i.e. parameters) to process different image regions. Moreover, we introduce a meta-learning defocus mask generation algorithm to assign each pixel to a proper branch. In this way, we can expect to well maintain the information of the clear regions while recovering the missing details of the blurred regions. Both quantitative and qualitative experiments demonstrate that our BaMBNet outperforms the state-of-the-art methods. Source code will be available at https://github.com/junjun-jiang/BaMBNet.

READ FULL TEXT

page 1

page 4

page 8

page 9

page 10

research
05/01/2020

Defocus Deblurring Using Dual-Pixel Data

Defocus blur arises in images that are captured with a shallow depth of ...
research
07/19/2023

LDP: Language-driven Dual-Pixel Image Defocus Deblurring Network

Recovering sharp images from dual-pixel (DP) pairs with disparity-depend...
research
08/12/2020

Select Good Regions for Deblurring based on Convolutional Neural Networks

The goal of blind image deblurring is to recover sharp image from one in...
research
05/14/2021

End-to-end Alternating Optimization for Blind Super Resolution

Previous methods decompose the blind super-resolution (SR) problem into ...
research
04/26/2022

Learning Dual-Pixel Alignment for Defocus Deblurring

It is a challenging task to recover all-in-focus image from a single def...
research
04/06/2022

Multi-Scale Memory-Based Video Deblurring

Video deblurring has achieved remarkable progress thanks to the success ...
research
11/25/2022

Learnable Blur Kernel for Single-Image Defocus Deblurring in the Wild

Recent research showed that the dual-pixel sensor has made great progres...

Please sign up or login with your details

Forgot password? Click here to reset