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 2211–2220 of 3874 papers

TitleStatusHype
Fingerprinting Deep Image Restoration Models—0
Spectral Bayesian Uncertainty for Image Super-Resolution—0
HSR-Diff: Hyperspectral Image Super-Resolution via Conditional Diffusion Models—0
AccelIR: Task-Aware Image Compression for Accelerating Neural Restoration—0
One-Shot Model for Mixed-Precision Quantization—0
Toward Accurate Post-Training Quantization for Image Super ResolutionCode0
Diffusion-Based Signed Distance Fields for 3D Shape Generation—0
EfficientViT: Lightweight Multi-Scale Attention for High-Resolution Dense Prediction—0
Multi-Frequency Representation Enhancement with Privilege Information for Video Super-Resolution—0
Self-Supervised Burst Super-Resolution—0
Show:102550
← PrevPage 222 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified