SOTAVerified

Super-Resolution

Super-Resolution is a task in computer vision that involves increasing the resolution of an image or video by generating missing high-frequency details from low-resolution input. The goal is to produce an output image with a higher resolution than the input image, while preserving the original content and structure.

( Credit: MemNet )

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 51–75 of 3874 papers

TitleStatusHype
Omnidirectional Video Super-Resolution using Deep Learning—0
A Tree-guided CNN for image super-resolutionCode1
A Survey of Deep Learning Video Super-Resolution—0
Application of convolutional neural networks in image super-resolution—0
NTIRE 2025 Challenge on RAW Image Restoration and Super-Resolution—0
Model-Guided Network with Cluster-Based Operators for Spatio-Spectral Super-ResolutionCode0
Beyond Pretty Pictures: Combined Single- and Multi-Image Super-resolution for Sentinel-2 Images—0
Advancing Image Super-resolution Techniques in Remote Sensing: A Comprehensive Survey—0
SeG-SR: Integrating Semantic Knowledge into Remote Sensing Image Super-Resolution via Vision-Language ModelCode0
TextSR: Diffusion Super-Resolution with Multilingual OCR Guidance—0
Cascaded 3D Diffusion Models for Whole-body 3D 18-F FDG PET/CT synthesis from Demographics—0
Surf2CT: Cascaded 3D Flow Matching Models for Torso 3D CT Synthesis from Skin Surface—0
Label-free Super-Resolution Microvessel Color Flow Imaging with Ultrasound—0
DiMoSR: Feature Modulation via Multi-Branch Dilated Convolutions for Efficient Image Super-ResolutionCode1
UltraVSR: Achieving Ultra-Realistic Video Super-Resolution with Efficient One-Step Diffusion Space—0
Burst Image Super-Resolution via Multi-Cross Attention Encoding and Multi-Scan State-Space Decoding—0
Deep Spectral Prior—0
Memory-Efficient Super-Resolution of 3D Micro-CT Images Using Octree-Based GANs: Enhancing Resolution and Segmentation Accuracy—0
Chain-of-Zoom: Extreme Super-Resolution via Scale Autoregression and Preference Alignment—0
SuperGS: Consistent and Detailed 3D Super-Resolution Scene Reconstruction via Gaussian Splatting—0
SUFFICIENT: A scan-specific unsupervised deep learning framework for high-resolution 3D isotropic fetal brain MRI reconstruction—0
DOVE: Efficient One-Step Diffusion Model for Real-World Video Super-ResolutionCode2
Deep Learning-Driven Ultra-High-Definition Image Restoration: A SurveyCode1
Joint Flow And Feature Refinement Using Attention For Video Restoration—0
SuperPure: Efficient Purification of Localized and Distributed Adversarial Patches via Super-Resolution GAN Models—0
Show:102550
← PrevPage 3 of 155Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified