SwinFSR: Stereo Image Super-Resolution using SwinIR and Frequency Domain Knowledge

Chen, Ke; Li, Liangyan; Huan, Liu; Li, Yunzhe; Tang, Congling; Chen, Jun

doi:10.1109/cvprw59228.2023.00177

Search citation statements

Order By: Relevance

Paper Sections

Select...

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2023

2025

Publication Types

Select...

Other3

Article2

Relationship

Self Cite0

Independent5

Authors

Journals

Cited by 8 publications

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

Multidimensional fusion of frequency and spatial domain information for enhanced camouflaged object detection

Wang,

Yu,

Fang

et al. 2025

Information Fusion

View full text Add to dashboard Cite

Multidimensional fusion of frequency and spatial domain information for enhanced camouflaged object detection

Wang,

Yu,

Fang

et al. 2025

Information Fusion

View full text Add to dashboard Cite

Learning accurate and enriched features for stereo image super-resolution

Gao,

Dang

2025

Pattern Recognition

View full text Add to dashboard Cite

NTIRE 2023 Challenge on Stereo Image Super-Resolution: Methods and Results

Wang¹,

Guo²,

Wang³

et al. 2023

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

View full text Add to dashboard Cite

This paper summarizes the 3rd NTIRE challenge on stereo image super-resolution (SR) with a focus on new solutions and results. The task of this challenge is to super-resolve a low-resolution stereo image pair to a highresolution one with a magnification factor of ×4 under a limited computational budget. Compared with single image SR, the major challenge of this challenge lies in how to exploit additional information in another viewpoint and how to maintain stereo consistency in the results. This challenge has 2 tracks, including one track on bicubic degradation and one track on real degradations. In total, 108 and 70 participants were successfully registered for each track, respectively. In the test phase, 14 and 13 teams successfully submitted valid results with PSNR (RGB) scores better than the baseline. This challenge establishes a new benchmark for stereo image SR.

show abstract

SwinFSR: Stereo Image Super-Resolution using SwinIR and Frequency Domain Knowledge

Cited by 8 publications

References 33 publications

Multidimensional fusion of frequency and spatial domain information for enhanced camouflaged object detection

Multidimensional fusion of frequency and spatial domain information for enhanced camouflaged object detection

Learning accurate and enriched features for stereo image super-resolution

NTIRE 2023 Challenge on Stereo Image Super-Resolution: Methods and Results

Contact Info

Product

Resources

About