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 1021–1030 of 3874 papers

TitleStatusHype
HD-Painter: High-Resolution and Prompt-Faithful Text-Guided Image Inpainting with Diffusion ModelsCode2
ECAMP: Entity-centered Context-aware Medical Vision Language Pre-trainingCode1
EPNet: An Efficient Pyramid Network for Enhanced Single-Image Super-Resolution with Reduced Computational Requirements—0
Joint Range-Velocity-Azimuth Estimation for OFDM-Based Integrated Sensing and Communication—0
A 3D super-resolution of wind fields via physics-informed pixel-wise self-attention generative adversarial network—0
Learning Exhaustive Correlation for Spectral Super-Resolution: Where Spatial-Spectral Attention Meets Linear Dependence—0
How Good Are Deep Generative Models for Solving Inverse Problems?—0
ZS-SRT: An Efficient Zero-Shot Super-Resolution Training Method for Neural Radiance Fields—0
Scale-Equivariant Imaging: Self-Supervised Learning for Image Super-Resolution and DeblurringCode1
SPIRE: Semantic Prompt-Driven Image Restoration—0
Show:102550
← PrevPage 103 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified