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 1711–1720 of 3874 papers

TitleStatusHype
Downscaled Representation Matters: Improving Image Rescaling with Collaborative Downscaled Images—0
Semantic Encoder Guided Generative Adversarial Face Ultra-Resolution Network—0
Stereo Image Rain Removal via Dual-View Mutual Attention—0
RDRN: Recursively Defined Residual Network for Image Super-Resolution—0
Hard Exudate Segmentation Supplemented by Super-Resolution with Multi-scale Attention Fusion ModuleCode1
Conffusion: Confidence Intervals for Diffusion ModelsCode1
Super-resolution Reconstruction of Single Image for Latent features—0
Consistent Direct Time-of-Flight Video Depth Super-ResolutionCode1
SATVSR: Scenario Adaptive Transformer for Cross Scenarios Video Super-Resolution—0
CaDM: Codec-aware Diffusion Modeling for Neural-enhanced Video Streaming—0
Show:102550
← PrevPage 172 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified