arrow
返回

Toward Blind Flare Removal Using Knowledge-Driven Flare-Level Estimator

delete2024-01-01
delete0
PRE
AI
H
Haoyou Deng
L
Lida Li
F
Feng Zhang
Z
Zhiqiang Li
X
Xu Bin
Q
Qingbo Lu
C
Changxin Gao
N
Nong Sang *
DOI:10.1109/TIP.2024.3480696delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
Lens flare is a common phenomenon when strong light rays arrive at the camera sensor and a clean scene is consequently mixed up with various opaque and semi-transparent artifacts. Existing deep learning methods are always constrained with limited real image pairs for training. Though recent synthesis-based approaches are found effective, synthesized pairs still deviate from the real ones as the mixing mechanism of flare artifacts and scenes in the wild always depends on a line of undetermined factors, such as lens structure, scratches, etc. In this paper, we present a new perspective from the blind nature of the flare removal task in a knowledge-driven manner. Specifically, we present a simple yet effective flare-level estimator to predict the corruption level of a flare-corrupted image. The estimated flare-level can be interpreted as additive information of the gap between corrupted images and their flare-free correspondences to facilitate a network at both training and testing stages adaptively. Besides, we utilize a flare-level modulator to better integrate the estimations into networks. We also devise a flare-aware block for more accurate flare recognition and reconstruction. Additionally, we collect a new real-world flare dataset for benchmarking, namely WiderFlare. Extensive experiments on three benchmark datasets demonstrate that our method outperforms state-of-the-art methods quantitatively and qualitatively.
Keyword:
Training
Scattering
Lenses
Image restoration
Cameras
Deep learning
Shape
Light sources
Image reconstruction
Feature extraction
Flare removal
flare-level estimation
image restoration

期刊

IEEE Transactions on Image Processing 封面图
IEEE Transactions on Image Processing
IF:
13.7
论文数:
1.0W
被引数:
8.4W

机构

暂无机构信息
引用论文

引用论文

To Tap or Not to Tap…
err1973-08-01
err0
PREAI
errV. J. Gururaj; Raymond M. Russo; John E. Allen; Rozalia Herszkowicz
err分享
err收藏
Accelerated Cell Death in Podospora Autophagy Mutants
err2005-11-01
err0
errOAAI
errBérangère Pinan-Lucarré; Axelle Balguerie; Corinne Clavé
err分享
err收藏
err分享
err收藏
Fatal Aluminum Phosphide Poisoning
err2000-03-01
err0
errOAAI
errF. Anger; F. Paysant; F. Brousse; I. L. Normand; P. Develay; Y. Galliard; A. Baert; M. A. Le Gueut; G. Pepin; J.-P. Anger
err分享
err收藏
err分享
err收藏
学者 查看更多内容