2022
DOI: 10.1007/978-3-031-16434-7_47
|View full text |Cite
|
Sign up to set email alerts
|

Structure-Consistent Restoration Network for Cataract Fundus Image Enhancement

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1

Citation Types

0
2
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
5
2

Relationship

0
7

Authors

Journals

citations
Cited by 21 publications
(2 citation statements)
references
References 22 publications
0
2
0
Order By: Relevance
“…Built on this same degradation pipeline, Liu et al propose the Pyramid Constraint Network (PCENet) to enhance clinically-relevant representation [16]. Li et al present the Structure-Consistent Restoration Network (SCRNet) for cataract fundus images, which lays its foundation on the consistency of high-frequency components [13]. On the other hand, unpaired image translation based enhancement methods rely on adversarial training and do not require explicit modeling of image degradation.…”
Section: Introductionmentioning
confidence: 99%
“…Built on this same degradation pipeline, Liu et al propose the Pyramid Constraint Network (PCENet) to enhance clinically-relevant representation [16]. Li et al present the Structure-Consistent Restoration Network (SCRNet) for cataract fundus images, which lays its foundation on the consistency of high-frequency components [13]. On the other hand, unpaired image translation based enhancement methods rely on adversarial training and do not require explicit modeling of image degradation.…”
Section: Introductionmentioning
confidence: 99%
“…Traditional fundus image enhancement methods [3]- [6] were mainly based on handcrafted priors, and they could not satisfactorily handle the complexity of varied low-quality cases. To solve this issue, the deep learning methods were proposed to learn more general priors from large amounts of paired low-quality and highquality images [7]- [14]. Therefore, the existing methods resort to either i) synthetic image pairs, such as synthesizing lowquality fundus images by degrading real high-quality ones [7], or ii) unpaired supervision models, such as CycleGAN-like ones [11], [15], for enhancement.…”
mentioning
confidence: 99%