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 1631–1640 of 3874 papers

TitleStatusHype
Discretization-Induced Dirichlet Posterior for Robust Uncertainty Quantification on RegressionCode0
Accurate Image Super-Resolution Using Very Deep Convolutional NetworksCode0
High-throughput, high-resolution registration-free generated adversarial network microscopyCode0
Hyperspectral and multispectral image fusion with arbitrary resolution through self-supervised representationsCode0
Image Super-Resolution via Attention based Back Projection NetworksCode0
MetH: A family of high-resolution and variable-shape image challengesCode0
S2R: Exploring a Double-Win Transformer-Based Framework for Ideal and Blind Super-ResolutionCode0
Direction-of-arrival estimation with conventional co-prime arrays using deep learning-based probablistic Bayesian neural networks—0
Directional diffusion models for graph representation learning—0
Directing Mamba to Complex Textures: An Efficient Texture-Aware State Space Model for Image Restoration—0
Show:102550
← PrevPage 164 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified