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 431–440 of 3874 papers

TitleStatusHype
EDVR: Video Restoration with Enhanced Deformable Convolutional NetworksCode1
Decoupled Data Consistency with Diffusion Purification for Image RestorationCode1
Blockwise Parallel Decoding for Deep Autoregressive ModelsCode1
Benchmark Dataset and Effective Inter-Frame Alignment for Real-World Video Super-ResolutionCode1
Accelerating Diffusion Models for Inverse Problems through Shortcut SamplingCode1
Fast Generation of High Fidelity RGB-D Images by Deep-Learning with Adaptive ConvolutionCode1
DeblurSR: Event-Based Motion Deblurring Under the Spiking RepresentationCode1
Fast Neural Representations for Direct Volume RenderingCode1
A Lightweight Recurrent Aggregation Network for Satellite Video Super-ResolutionCode1
DDistill-SR: Reparameterized Dynamic Distillation Network for Lightweight Image Super-ResolutionCode1
Show:102550
← PrevPage 44 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified