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 2521–2530 of 3874 papers

TitleStatusHype
Channel-Partitioned Windowed Attention And Frequency Learning for Single Image Super-Resolution—0
One Model for Two Tasks: Cooperatively Recognizing and Recovering Low-Resolution Scene Text Images by Iterative Mutual Guidance—0
ACNPU: A 4.75TOPS/W 1080P@30FPS Super Resolution Accelerator with Decoupled Asymmetric Convolution—0
UltraVSR: Achieving Ultra-Realistic Video Super-Resolution with Efficient One-Step Diffusion Space—0
One-Shot Image Restoration—0
One-Shot Model for Mixed-Precision Quantization—0
Channel Attention based Iterative Residual Learning for Depth Map Super-Resolution—0
Channel Attention and Multi-level Features Fusion for Single Image Super-Resolution—0
Chain-of-Zoom: Extreme Super-Resolution via Scale Autoregression and Preference Alignment—0
CG-3DSRGAN: A classification guided 3D generative adversarial network for image quality recovery from low-dose PET images—0
Show:102550
← PrevPage 253 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified