Pith. sign in

REVIEW 12 cited by

SwinIR: Image Restoration Using Swin Transformer

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2108.10257 v1 pith:VJMGOASS submitted 2021-08-23 eess.IV cs.CV

classification eess.IVcs.CV
keywords imagerestorationswinswinirtransformerextractionfeatureimages
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

Image restoration is a long-standing low-level vision problem that aims to restore high-quality images from low-quality images (e.g., downscaled, noisy and compressed images). While state-of-the-art image restoration methods are based on convolutional neural networks, few attempts have been made with Transformers which show impressive performance on high-level vision tasks. In this paper, we propose a strong baseline model SwinIR for image restoration based on the Swin Transformer. SwinIR consists of three parts: shallow feature extraction, deep feature extraction and high-quality image reconstruction. In particular, the deep feature extraction module is composed of several residual Swin Transformer blocks (RSTB), each of which has several Swin Transformer layers together with a residual connection. We conduct experiments on three representative tasks: image super-resolution (including classical, lightweight and real-world image super-resolution), image denoising (including grayscale and color image denoising) and JPEG compression artifact reduction. Experimental results demonstrate that SwinIR outperforms state-of-the-art methods on different tasks by $\textbf{up to 0.14$\sim$0.45dB}$, while the total number of parameters can be reduced by $\textbf{up to 67%}$.

Discussion (0). Sign in to comment.

Forward citations

Cited by 12 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Hierarchical Image Tokenization for Multi-Scale Image Super Resolution

    cs.CV 2026-05 unverdicted novelty 7.0 of 10

    HIT with token overlap plus DPO regularization lets a 300M-param VAR model deliver state-of-the-art multi-scale ISR in one forward pass without external data.

  2. LucidFlux: Caption-Free Photo-Realistic Image Restoration via a Large-Scale Diffusion Transformer

    cs.CV 2025-09 unverdicted novelty 7.0 of 10

    LucidFlux is a caption-free image restoration method that conditions a Flux.1 diffusion transformer with a dual-branch module from the degraded input and a proxy restoration plus SigLIP semantic features to outperform...

  3. Loggia dei Lanzi: AI Thermography Enhancement Comparisons through 3D Photogrammetry

    cs.CV 2026-08 conditional novelty 6.0 of 10

    For thermal photogrammetry of heritage buildings, AI super-resolution degrades 3D reconstruction quality; native-resolution thermal images remain the most geometrically accurate, and hardware UltraMax offers only marg...

  4. SR-Ground: Image Quality Grounding for Super-Resolved Content

    cs.CV 2026-05 unverdicted novelty 6.0 of 10

    The paper releases SR-Ground, a crowdsourced dataset for pixel-level segmentation of six artifact types in super-resolved images, and shows its use for training grounded IQA models and artifact-reducing fine-tuning.

  5. Defining Robust Ultrasound Quality Metrics via an Ultrasound Foundation Model

    eess.IV 2026-04 unverdicted novelty 6.0 of 10

    Proposes TinyUSFM-uLPIPS and TinyUSFM-NRQ metrics that show better alignment with segmentation task performance and expert preference than PSNR or VGG-LPIPS in ultrasound imaging.

  6. Defining Robust Ultrasound Quality Metrics via an Ultrasound Foundation Model

    eess.IV 2026-04 unverdicted novelty 6.0 of 10

    TinyUSFM-uLPIPS and TinyUSFM-NRQ provide task-linked, cross-organ, and clinically predictive quality assessment for ultrasound images that outperforms conventional metrics in calibration with segmentation performance ...

  7. MatRes: Zero-Shot Test-Time Model Adaptation for Simultaneous Matching and Restoration

    cs.CV 2026-04 unverdicted novelty 6.0 of 10

    MatRes jointly optimizes restoration and correspondence estimation at test time by enforcing conditional similarity on a single image pair and adapting lightweight modules without offline training.

  8. NWaaS: A Non-Intrusive and Privacy-Preserving Watermarking-as-a-Service System with Adaptive Resource Scheduling

    cs.CR 2025-07 conditional novelty 6.0 of 10

    ShadowMark extracts a verifiable watermark from the API surrounding a frozen image model, using a secret-key generated input and a trained decoder.

  9. Small, Bias-Free, Blind and Convolutional Denoiser: A compact ConvNeXt U-Net for blind Gaussian color-image denoising

    eess.IV 2026-07 conditional novelty 5.0 of 10

    BF-ConvUNeXt, a 0.82M-parameter bias-free ConvNeXt U-Net, is degree-1 homogeneous and matches DnCNN/FFDNet in blind color denoising, extrapolating smoothly beyond its training noise range.

  10. Towards High-Resolution Alignment and Super-Resolution of Multi-Sensor Satellite Imagery

    eess.IV 2025-07 reject novelty 5.0 of 10

    A preliminary HLS30-to-HLS10 super-resolution pipeline shows histogram and feature distribution matching improve cross-sensor alignment, but the evaluation leaks target-image statistics and omits quantitative results ...

  11. Interest Entanglement: The Hidden Barrier to Blind Super-Resolution Optimization

    cs.CV 2026-06 unverdicted novelty 4.0 of 10

    Proposes the SFR framework and InfoSqueeze module to resolve Interest Entanglement by decoupling regression and perceptual objectives in image super-resolution through shared feature representations.

  12. Systematic Evaluation of Wavelet-Based Denoising for MRI Brain Images: Optimal Configurations and Performance Benchmarks

    eess.IV 2025-08 unverdicted novelty 4.0 of 10

    A systematic benchmark identifies bior6.8 biorthogonal wavelet with universal thresholding at decomposition levels 2-3 as the best wavelet denoising configuration for MRI brain images among those tested.

Pith tools