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 3331–3340 of 3874 papers

TitleStatusHype
Evaluating Robustness of Deep Image Super-Resolution against Adversarial AttacksCode0
Difficulty-aware Image Super Resolution via Deep Adaptive Dual-NetworkCode0
Label Super Resolution with Inter-Instance Loss—0
Data-Driven Design for Fourier Ptychographic Microscopy—0
Camera Lens Super-ResolutionCode0
Blind Super-Resolution With Iterative Kernel CorrectionCode0
Fast Spatio-Temporal Residual Network for Video Super-Resolution—0
Controlling Neural Networks via Energy Dissipation—0
Deep Back-Projection Networks for Single Image Super-resolutionCode0
Learning Implicit Generative Models by Matching Perceptual Features—0
Show:102550
← PrevPage 334 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified