Attacking Defocus Detection With Blur-Aware Transformation for Defocus Deblurring

Previous fully-supervised defocus deblurring has made significant progress. However, training such deep models requires abundant paired ground truth, which is expensive and error-prone. This paper makes an attempt to train a defocus deblurring model without using paired ground truth and any other un...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on multimedia Vol. 26; pp. 1 - 11
Main Authors: Zhao, Wenda, Hu, Guang, Wei, Fei, Wang, Haipeng, He, You, Lu, Huchuan
Format: Journal Article
Language:English
Published: Piscataway IEEE 01.01.2024
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
Blur-aware transfer
Bridges
Convolution
Defocus detection attack
Feature extraction
Generative adversarial networks
Robustness
Task analysis
Training
Weakly-supervised defocus deblurring
ISSN:1520-9210, 1941-0077
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Previous fully-supervised defocus deblurring has made significant progress. However, training such deep models requires abundant paired ground truth, which is expensive and error-prone. This paper makes an attempt to train a defocus deblurring model without using paired ground truth and any other unpaired data. Related reblur-to-deblur schemes generally use physics-based reblur or GAN-based reblur, suffering from the robustness of blur kernel and hallucination generated by GAN. Besides, the domain gap between the realistic blurred image and reblurred image hinders deblurring performance. Addressing these challenges, we propose a weakly-supervised defocus deblurring framework via defocus detection attack. On one hand, we build a focused area detection attack (FADA) to enforce the focused area to reblur, thereby reversing its detection result by a pretrained defocus blur detection network. Moreover, we introduce a blur-aware transfer modulated from the defocused region to help FADA render a robust reblurred region. On the other hand, we implement a defocused region detection attack to guide the realistic blurred region to deblur in the process of training deblurring network with simulated-paired areas. Extensive experiments on three widely-used datasets verify the effectiveness of our framework. Code is available at: https://github.com/wdzhao123/ADDBAT.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1520-9210
1941-0077
DOI:10.1109/TMM.2023.3334023