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 3091–3100 of 3874 papers

TitleStatusHype
Weak Texture Information Map Guided Image Super-resolution with Deep Residual Networks—0
Is There Tradeoff between Spatial and Temporal in Video Super-Resolution?—0
Pyramidal Edge-maps and Attention based Guided Thermal Super-resolution—0
Memory-efficient Learning for Large-scale Computational Imaging—0
FarSee-Net: Real-Time Semantic Segmentation by Efficient Multi-scale Context Aggregation and Feature Space Super-resolution—0
Semantic Object Prediction and Spatial Sound Super-Resolution with Binaural Sounds—0
Perceptual Image Super-Resolution with Progressive Adversarial Network—0
Super Resolution Using Segmentation-Prior Self-Attention Generative Adversarial Network—0
Turbulence Enrichment using Physics-informed Generative Adversarial Networks—0
VESR-Net: The Winning Solution to Youku Video Enhancement and Super-Resolution Challenge—0
Show:102550
← PrevPage 310 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified