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
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 $\textbf{up to 67%}$.
Forward citations
Cited by 12 Pith papers
-
Hierarchical Image Tokenization for Multi-Scale Image Super Resolution
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.
-
LucidFlux: Caption-Free Photo-Realistic Image Restoration via a Large-Scale Diffusion Transformer
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...
-
Loggia dei Lanzi: AI Thermography Enhancement Comparisons through 3D Photogrammetry
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...
-
SR-Ground: Image Quality Grounding for Super-Resolved Content
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.
-
Defining Robust Ultrasound Quality Metrics via an Ultrasound Foundation Model
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.
-
Defining Robust Ultrasound Quality Metrics via an Ultrasound Foundation Model
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 ...
-
MatRes: Zero-Shot Test-Time Model Adaptation for Simultaneous Matching and Restoration
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.
-
NWaaS: A Non-Intrusive and Privacy-Preserving Watermarking-as-a-Service System with Adaptive Resource Scheduling
ShadowMark extracts a verifiable watermark from the API surrounding a frozen image model, using a secret-key generated input and a trained decoder.
-
Small, Bias-Free, Blind and Convolutional Denoiser: A compact ConvNeXt U-Net for blind Gaussian color-image denoising
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.
-
Towards High-Resolution Alignment and Super-Resolution of Multi-Sensor Satellite Imagery
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 ...
-
Interest Entanglement: The Hidden Barrier to Blind Super-Resolution Optimization
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.
-
Systematic Evaluation of Wavelet-Based Denoising for MRI Brain Images: Optimal Configurations and Performance Benchmarks
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.
Discussion (0). Sign in to comment.