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 1711–1720 of 3874 papers

TitleStatusHype
CoReGAN: Contrastive Regularized Generative Adversarial Network for Guided Depth Map Super Resolution—0
In-Place Scene Labelling and Understanding with Implicit Scene Representation—0
Hyperspectral Image Restoration and Super-resolution with Physics-Aware Deep Learning for Biomedical Applications—0
Hyperspectral Image Super-Resolution in Arbitrary Input-Output Band Settings—0
Hyperspectral Image Super-resolution via Deep Spatio-spectral Convolutional Neural Networks—0
Feature Alignment with Equivariant Convolutions for Burst Image Super-Resolution—0
Feature Aggregating Network with Inter-Frame Interaction for Efficient Video Super-Resolution—0
Hyperspectral Image Super-Resolution via Dual-domain Network Based on Hybrid Convolution—0
FDAN: Flow-guided Deformable Alignment Network for Video Super-Resolution—0
A Sinkhorn Regularized Adversarial Network for Image Guided DEM Super-resolution using Frequency Selective Hybrid Graph Transformer—0
Show:102550
← PrevPage 172 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified