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 901–910 of 3874 papers

TitleStatusHype
Revisiting Temporal Modeling for Video Super-resolutionCode1
OverNet: Lightweight Multi-Scale Super-Resolution with Overscaling NetworkCode1
Component Divide-and-Conquer for Real-World Image Super-ResolutionCode1
Hierarchical Amortized Training for Memory-efficient High Resolution 3D GANCode1
Sub-Pixel Back-Projection Network For Lightweight Single Image Super-ResolutionCode1
Video Super-Resolution with Recurrent Structure-Detail NetworkCode1
PlugNet: Degradation Aware Scene Text Recognition Supervised by a Pluggable Super-Resolution UnitCode1
Spatial-Angular Interaction for Light Field Image Super-ResolutionCode1
Multi-Step Reinforcement Learning for Single Image Super-ResolutionCode1
Multi-Image Super-Resolution for Remote Sensing using Deep Recurrent NetworksCode1
Show:102550
← PrevPage 91 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified