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 2801–2810 of 3874 papers

TitleStatusHype
T2 Mapping from Super-Resolution-Reconstructed Clinical Fast Spin Echo Magnetic Resonance Acquisitions—0
Taming Stable Diffusion for Computed Tomography Blind Super-Resolution—0
TANet: A new Paradigm for Global Face Super-resolution via Transformer-CNN Aggregation Network—0
Task-Aware Image Downscaling—0
Task Decoupled Framework for Reference-Based Super-Resolution—0
Task-driven real-world super-resolution of document scans—0
Task-driven single-image super-resolution reconstruction of document scans—0
Task-Driven Super Resolution: Object Detection in Low-resolution Images—0
TcGAN: Semantic-Aware and Structure-Preserved GANs with Individual Vision Transformer for Fast Arbitrary One-Shot Image Generation—0
Tchebichef Transform Domain-based Deep Learning Architecture for Image Super-resolution—0
Show:102550
← PrevPage 281 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified