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 811–820 of 3874 papers

TitleStatusHype
Conditional Hyper-Network for Blind Super-Resolution with Multiple DegradationsCode1
NU-Wave: A Diffusion Probabilistic Model for Neural Audio UpsamplingCode1
Efficient Video Compression via Content-Adaptive Super-ResolutionCode1
High-resolution Depth Maps Imaging via Attention-based Hierarchical Multi-modal FusionCode1
Unsupervised Degradation Representation Learning for Blind Super-ResolutionCode1
RetrievalFuse: Neural 3D Scene Reconstruction with a DatabaseCode1
Best-Buddy GANs for Highly Detailed Image Super-ResolutionCode1
Flow-based Kernel Prior with Application to Blind Super-ResolutionCode1
Transitional Learning: Exploring the Transition States of Degradation for Blind Super-resolutionCode1
D2C-SR: A Divergence to Convergence Approach for Real-World Image Super-ResolutionCode1
Show:102550
← PrevPage 82 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified