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.
Swinir: Image restoration using swin transformer.arXiv preprint arXiv:2108.10257
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
verdicts
UNVERDICTED 6representative citing papers
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 baselines on synthetic and real-world data.
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.
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.
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.
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.
citing papers explorer
-
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 baselines on synthetic and real-world data.
-
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.
-
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.
-
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.