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 3781–3790 of 3874 papers

TitleStatusHype
EAGLE: Large-scale Vehicle Detection Dataset in Real-World Scenarios using Aerial Imagery—0
Generative Diffusion Prior for Unified Image Restoration and Enhancement—0
A Generative Model for Generic Light Field Reconstruction—0
Generative Powers of Ten—0
Generative VoxelNet: Learning Energy-Based Models for 3D Shape Synthesis and Analysis—0
Generator From Edges: Reconstruction of Facial Images—0
Generic 3D Convolutional Fusion for image restoration—0
Generic Perceptual Loss for Modeling Structured Output Dependencies—0
DynVideo-E: Harnessing Dynamic NeRF for Large-Scale Motion- and View-Change Human-Centric Video Editing—0
Dynamic super-resolution in particle tracking problems—0
Show:102550
← PrevPage 379 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified