Papers › Resolution Enhancement Processing on Low Quality Images Using Swin Transformer Based...

Resolution Enhancement Processing on Low Quality Images Using Swin Transformer Based on Interval Dense Connection Strategy

16 Mar 2023arXiv:2303.09190archive 2025-07-28

Rui-Yang Ju, Chih-Chia Chen, Jen-Shiun Chiang, Yu-Shian Lin, Wei-Han Chen, Chun-Tse Chien

The Transformer-based method has demonstrated remarkable performance for image super-resolution in comparison to the method based on the convolutional neural networks (CNNs). However, using the self-attention mechanism like SwinIR (Image Restoration Using Swin Transformer) to extract feature information from images needs a significant amount of computational resources, which limits its application on low computing power platforms. To improve the model feature reuse, this research work proposes the Interval Dense Connection Strategy, which connects different blocks according to the newly designed algorithm. We apply this strategy to SwinIR and present a new model, which named SwinOIR (Object Image Restoration Using Swin Transformer). For image super-resolution, an ablation study is conducted to demonstrate the positive effect of the Interval Dense Connection Strategy on the model performance. Furthermore, we evaluate our model on various popular benchmark datasets, and compare it with other state-of-the-art (SOTA) lightweight models. For example, SwinOIR obtains a PSNR of 26.62 dB for x4 upscaling image super-resolution on Urban100 dataset, which is 0.15 dB higher than the SOTA model SwinIR. For real-life application, this work applies the lastest version of You Only Look Once (YOLOv8) model and the proposed model to perform object detection and real-life image super-resolution on low-quality images. This implementation code is publicly available at https://github.com/Rubbbbbbbbby/SwinOIR.

PaperPDFCode

Code

rubbbbbbbbby/swinoir officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Image CroppingImage RestorationImage Super-ResolutionObject DetectionReal-Time Object DetectionSuper-Resolutionobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Super-Resolution BSD100 - 2x upscaling SwinOIR PSNR 32.34 #18 of 30 Archive leaderboard report
Image Super-Resolution BSD100 - 2x upscaling SwinOIR SSIM 0.9022 #18 of 30 Archive leaderboard report
Image Super-Resolution BSD100 - 3x upscaling SwinOIR PSNR 29.27 #13 of 21 Archive leaderboard report
Image Super-Resolution BSD100 - 3x upscaling SwinOIR SSIM 0.8111 #13 of 21 Archive leaderboard report
Image Super-Resolution BSD100 - 4x upscaling SwinOIR PSNR 27.76 #23 of 71 Archive leaderboard report
Image Super-Resolution BSD100 - 4x upscaling SwinOIR SSIM 0.7441 #23 of 71 Archive leaderboard report
Image Super-Resolution Set14 - 2x upscaling SwinOIR PSNR 33.97 #18 of 35 Archive leaderboard report
Image Super-Resolution Set14 - 2x upscaling SwinOIR SSIM 0.922 #18 of 35 Archive leaderboard report
Image Super-Resolution Set14 - 3x upscaling SwinOIR PSNR 30.65 #14 of 24 Archive leaderboard report
Image Super-Resolution Set14 - 3x upscaling SwinOIR SSIM 0.8493 #14 of 24 Archive leaderboard report
Image Super-Resolution Set14 - 4x upscaling SwinOIR PSNR 28.92 #38 of 104 Archive leaderboard report
Image Super-Resolution Set14 - 4x upscaling SwinOIR SSIM 0.7892 #38 of 104 Archive leaderboard report
Image Super-Resolution Set5 - 2x upscaling SwinOIR PSNR 38.21 #20 of 41 Archive leaderboard report
Image Super-Resolution Set5 - 2x upscaling SwinOIR SSIM 0.9614 #20 of 41 Archive leaderboard report
Image Super-Resolution Set5 - 3x upscaling SwinOIR PSNR 34.69 #19 of 32 Archive leaderboard report
Image Super-Resolution Set5 - 3x upscaling SwinOIR SSIM 0.9296 #19 of 32 Archive leaderboard report
Image Super-Resolution Urban100 - 2x upscaling SwinOIR PSNR 32.83 #20 of 29 Archive leaderboard report
Image Super-Resolution Urban100 - 2x upscaling SwinOIR SSIM 0.9353 #20 of 29 Archive leaderboard report
Image Super-Resolution Urban100 - 3x upscaling SwinOIR PSNR 28.87 #15 of 22 Archive leaderboard report
Image Super-Resolution Urban100 - 3x upscaling SwinOIR SSIM 0.8674 #15 of 22 Archive leaderboard report
Image Super-Resolution Urban100 - 4x upscaling SwinOIR PSNR 26.74 #28 of 65 Archive leaderboard report
Image Super-Resolution Urban100 - 4x upscaling SwinOIR SSIM 0.806 #28 of 65 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxStochastic DepthSwin TransformerTransformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections