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

Showing 601610 of 3874 papers

TitleStatusHype
Learning Mutual Modulation for Self-Supervised Cross-Modal Super-ResolutionCode1
Deep Semantic Statistics Matching (D2SM) Denoising NetworkCode1
Boosting Video Super Resolution with Patch-Based Temporal Redundancy OptimizationCode1
Enhancing Space-time Video Super-resolution via Spatial-temporal Feature InteractionCode1
Rethinking Alignment in Video Super-Resolution TransformersCode1
Single MR Image Super-Resolution using Generative Adversarial NetworkCode1
Quality Assessment of Image Super-Resolution: Balancing Deterministic and Statistical FidelityCode1
BayesCap: Bayesian Identity Cap for Calibrated Uncertainty in Frozen Neural NetworksCode1
Cross-receptive Focused Inference Network for Lightweight Image Super-ResolutionCode1
Deep Parametric 3D Filters for Joint Video Denoising and Illumination Enhancement in Video Super ResolutionCode1
Show:102550
← PrevPage 61 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41Unverified