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 661–670 of 3874 papers

TitleStatusHype
Restore-RWKV: Efficient and Effective Medical Image Restoration with RWKVCode2
Arbitrary-Scale Video Super-Resolution with Structural and Textural PriorsCode2
Task-driven single-image super-resolution reconstruction of document scans—0
Region Attention Transformer for Medical Image RestorationCode1
Global Spatial-Temporal Information-based Residual ConvLSTM for Video Space-Time Super-Resolution—0
Spatially-Variant Degradation Model for Dataset-free Super-resolutionCode0
VEnhancer: Generative Space-Time Enhancement for Video Generation—0
Pairwise Distance Distillation for Unsupervised Real-World Image Super-ResolutionCode1
UnmixingSR: Material-aware Network with Unsupervised Unmixing as Auxiliary Task for Hyperspectral Image Super-resolution—0
Neuromorphic Imaging with Super-Resolution—0
Show:102550
← PrevPage 67 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified