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 541–550 of 3874 papers

TitleStatusHype
Finding Discriminative Filters for Specific Degradations in Blind Super-ResolutionCode1
Flexible Style Image Super-Resolution using Conditional ObjectiveCode1
CoReFusion: Contrastive Regularized Fusion for Guided Thermal Super-ResolutionCode1
3D Human Shape and Pose from a Single Low-Resolution Image with Self-Supervised LearningCode1
FedVSR: Towards Model-Agnostic Federated Learning in Video Super-ResolutionCode1
Convolutional Neural Networks with Intermediate Loss for 3D Super-Resolution of CT and MRI ScansCode1
Advancing High-Resolution Video-Language Representation with Large-Scale Video TranscriptionsCode1
Cross-sensor super-resolution of irregularly sampled Sentinel-2 time seriesCode1
Feedback Network for Mutually Boosted Stereo Image Super-Resolution and Disparity EstimationCode1
Flow-based Kernel Prior with Application to Blind Super-ResolutionCode1
Show:102550
← PrevPage 55 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified