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 3261–3270 of 3874 papers

TitleStatusHype
RankSRGAN: Generative Adversarial Networks with Ranker for Image Super-ResolutionCode0
Image Formation Model Guided Deep Image Super-ResolutionCode0
Deep Slice Interpolation via Marginal Super-Resolution, Fusion and Refinement—0
Super-resolution of Omnidirectional Images Using Adversarial LearningCode0
Jointly Aligning Millions of Images with Deep Penalised Reconstruction Congealing—0
Manifold Modeling in Embedded Space: A Perspective for Interpreting Deep Image PriorCode0
Attention-Aware Linear Depthwise Convolution for Single Image Super-Resolution—0
Architecture-aware Network Pruning for Vision Quality Applications—0
Multi-Contrast Super-Resolution MRI Through a Progressive Network—0
CRNet: Image Super-Resolution Using A Convolutional Sparse Coding Inspired Network—0
Show:102550
← PrevPage 327 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified