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 271–280 of 3874 papers

TitleStatusHype
Cascaded Temporal Updating Network for Efficient Video Super-ResolutionCode1
MambaCSR: Dual-Interleaved Scanning for Compressed Image Super-Resolution With SSMsCode1
Implicit Grid Convolution for Multi-Scale Image Super-ResolutionCode1
GRFormer: Grouped Residual Self-Attention for Lightweight Single Image Super-ResolutionCode1
One Step Diffusion-based Super-Resolution with Time-Aware DistillationCode1
Attention Beats Linear for Fast Implicit Neural Representation GenerationCode1
A New Dataset and Framework for Real-World Blurred Images Super-ResolutionCode1
Large Kernel Distillation Network for Efficient Single Image Super-ResolutionCode1
MaRINeR: Enhancing Novel Views by Matching Rendered Images with Nearby ReferencesCode1
Region Attention Transformer for Medical Image RestorationCode1
Show:102550
← PrevPage 28 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified