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 2551–2560 of 3874 papers

TitleStatusHype
Efficient Video Compression via Content-Adaptive Super-ResolutionCode1
High-resolution Depth Maps Imaging via Attention-based Hierarchical Multi-modal FusionCode1
SDAN: Squared Deformable Alignment Network for Learning Misaligned Optical ZoomCode0
Unsupervised Degradation Representation Learning for Blind Super-ResolutionCode1
RetrievalFuse: Neural 3D Scene Reconstruction with a DatabaseCode1
MR Slice Profile Estimation by Learning to Match Internal Patch DistributionsCode0
Video-Specific Autoencoders for Exploring, Editing and Transmitting Videos—0
Near field Acoustic Holography on arbitrary shapes using Convolutional Neural NetworkCode0
In-Place Scene Labelling and Understanding with Implicit Scene Representation—0
Flow-based Kernel Prior with Application to Blind Super-ResolutionCode1
Show:102550
← PrevPage 256 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified