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 581–590 of 3874 papers

TitleStatusHype
CVAE-GAN: Fine-Grained Image Generation through Asymmetric TrainingCode1
Global field reconstruction from sparse sensors with Voronoi tessellation-assisted deep learningCode1
DeblurSR: Event-Based Motion Deblurring Under the Spiking RepresentationCode1
GRFormer: Grouped Residual Self-Attention for Lightweight Single Image Super-ResolutionCode1
CHIMLE: Conditional Hierarchical IMLE for Multimodal Conditional Image SynthesisCode1
CiaoSR: Continuous Implicit Attention-in-Attention Network for Arbitrary-Scale Image Super-ResolutionCode1
Decomposition-Based Variational Network for Multi-Contrast MRI Super-Resolution and ReconstructionCode1
Simultaneous Image-to-Zero and Zero-to-Noise: Diffusion Models with Analytical Image AttenuationCode1
Generalized Real-World Super-Resolution through Adversarial RobustnessCode1
Generative Adversarial Super-Resolution at the Edge with Knowledge DistillationCode1
Show:102550
← PrevPage 59 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified