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 171–180 of 3874 papers

TitleStatusHype
Open High-Resolution Satellite Imagery: The WorldStrat Dataset -- With Application to Super-ResolutionCode2
NU-Wave 2: A General Neural Audio Upsampling Model for Various Sampling RatesCode2
AnimeSR: Learning Real-World Super-Resolution Models for Animation VideosCode2
VideoINR: Learning Video Implicit Neural Representation for Continuous Space-Time Super-ResolutionCode2
Decoupled-and-Coupled Networks: Self-Supervised Hyperspectral Image Super-Resolution with Subpixel FusionCode2
CogView2: Faster and Better Text-to-Image Generation via Hierarchical TransformersCode2
On the Generalization of BasicVSR++ to Video Deblurring and DenoisingCode2
Learning Trajectory-Aware Transformer for Video Super-ResolutionCode2
Reference-based Video Super-Resolution Using Multi-Camera Video TripletsCode2
Details or Artifacts: A Locally Discriminative Learning Approach to Realistic Image Super-ResolutionCode2
Show:102550
← PrevPage 18 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified