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 501–510 of 3874 papers

TitleStatusHype
Learning Non-Local Spatial-Angular Correlation for Light Field Image Super-ResolutionCode1
Hyperspectral Image Super Resolution with Real Unaligned RGB GuidanceCode1
Towards Geospatial Foundation Models via Continual PretrainingCode1
Hypernetworks build Implicit Neural Representations of SoundsCode1
OSRT: Omnidirectional Image Super-Resolution with Distortion-aware TransformerCode1
Accelerating Guided Diffusion Sampling with Splitting Numerical MethodsCode1
Deep Diversity-Enhanced Feature Representation of Hyperspectral ImagesCode1
Learning Continuous Mesh Representation with Spherical Implicit SurfaceCode1
WIRE: Wavelet Implicit Neural RepresentationsCode1
Boosting Single Image Super-Resolution via Partial Channel ShiftingCode1
Show:102550
← PrevPage 51 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified