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 1941–1950 of 3874 papers

TitleStatusHype
NU-Wave 2: A General Neural Audio Upsampling Model for Various Sampling RatesCode2
Real-World Single Image Super-Resolution Under Rainy Condition—0
GRAM-HD: 3D-Consistent Image Generation at High Resolution with Generative Radiance Manifolds—0
Super-resolution image display using diffractive decoders—0
Subsurface Depths Structure Maps Reconstruction with Generative Adversarial Networks—0
Structured Sparsity Learning for Efficient Video Super-ResolutionCode1
AnimeSR: Learning Real-World Super-Resolution Models for Animation VideosCode2
Hypernetwork-Based Adaptive Image RestorationCode1
Real-World Light Field Image Super-Resolution via Degradation ModulationCode1
RPLHR-CT Dataset and Transformer Baseline for Volumetric Super-Resolution from CT ScansCode1
Show:102550
← PrevPage 195 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified