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 1981–1990 of 3874 papers

TitleStatusHype
Deep Networks for Image Super-Resolution with Sparse Prior—0
Large Motion Video Super-Resolution with Dual Subnet and Multi-Stage Communicated Upsampling—0
Large Receptive Field Networks for High-Scale Image Super-Resolution—0
Large-scale single-photon imaging—0
Towards Realistic Data Generation for Real-World Super-Resolution—0
LASSR: Effective Super-Resolution Method for Plant Disease Diagnosis—0
Adaptive Multi-modal Fusion of Spatially Variant Kernel Refinement with Diffusion Model for Blind Image Super-Resolution—0
Deep Networks for Image and Video Super-Resolution—0
Latent Multi-Relation Reasoning for GAN-Prior based Image Super-Resolution—0
Latent-Shift: Latent Diffusion with Temporal Shift for Efficient Text-to-Video Generation—0
Show:102550
← PrevPage 199 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified