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 1611–1620 of 3874 papers

TitleStatusHype
Lightweight Image Super-Resolution with Superpixel Token InteractionCode1
Content-Aware Local GAN for Photo-Realistic Super-Resolution—0
Self-Supervised Burst Super-Resolution—0
EfficientViT: Lightweight Multi-Scale Attention for High-Resolution Dense Prediction—0
Rethinking Multi-Contrast MRI Super-Resolution: Rectangle-Window Cross-Attention Transformer and Arbitrary-Scale UpsamplingCode1
Pyramid Dual Domain Injection Network for Pan-sharpening—0
PIRNet: Privacy-Preserving Image Restoration Network via Wavelet Lifting—0
Diffusion-Based Signed Distance Fields for 3D Shape Generation—0
Deep Random Projector: Accelerated Deep Image PriorCode1
Azimuth Super-Resolution for FMCW Radar in Autonomous DrivingCode1
Show:102550
← PrevPage 162 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified