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 1871–1880 of 3874 papers

TitleStatusHype
Online Video Super-Resolution with Convolutional Kernel Bypass Graft—0
Latent Multi-Relation Reasoning for GAN-Prior based Image Super-Resolution—0
Pyramidal Denoising Diffusion Probabilistic Models—0
Physics-informed Deep Super-resolution for Spatiotemporal DataCode1
Robust Real-World Image Super-Resolution against Adversarial AttacksCode1
High Dynamic Range and Super-Resolution from Raw Image Bursts—0
GLEAN: Generative Latent Bank for Image Super-Resolution and BeyondCode5
Meta-Learning based Degradation Representation for Blind Super-ResolutionCode1
Criteria Comparative Learning for Real-scene Image Super-ResolutionCode0
Learning Series-Parallel Lookup Tables for Efficient Image Super-ResolutionCode0
Show:102550
← PrevPage 188 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified