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 211–220 of 3874 papers

TitleStatusHype
RainScaleGAN: a Conditional Generative Adversarial Network for Rainfall DownscalingCode0
C2D-ISR: Optimizing Attention-based Image Super-resolution from Continuous to Discrete Scales—0
Rethinking Image Evaluation in Super-Resolution—0
FedVSR: Towards Model-Agnostic Federated Learning in Video Super-ResolutionCode1
QDM: Quadtree-Based Region-Adaptive Sparse Diffusion Models for Efficient Image Super-ResolutionCode1
ECLARE: Efficient cross-planar learning for anisotropic resolution enhancementCode0
Perceive, Understand and Restore: Real-World Image Super-Resolution with Autoregressive Multimodal Generative ModelsCode2
ReCamMaster: Camera-Controlled Generative Rendering from A Single Video—0
Toward Generalized Image Quality Assessment: Relaxing the Perfect Reference Quality AssumptionCode2
Fourier Neural Operator based surrogates for CO_2 storage in realistic geologies—0
Show:102550
← PrevPage 22 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified