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 2791–2800 of 3874 papers

TitleStatusHype
Local-Global Fusion Network for Video Super-ResolutionCode1
NEMO: enabling neural-enhanced video streaming on commodity mobile devicesCode1
Reconstruct high-resolution multi-focal plane images from a single 2D wide field image—0
AdderSR: Towards Energy Efficient Image Super-Resolution—0
DeepRemaster: Temporal Source-Reference Attention Networks for Comprehensive Video Enhancement—0
Searching for Low-Bit Weights in Quantized Neural NetworksCode1
Parallax Attention for Unsupervised Stereo Correspondence LearningCode1
Multiple Exemplars-based Hallucinationfor Face Super-resolution and Editing—0
AIM 2020 Challenge on Efficient Super-Resolution: Methods and ResultsCode2
Understanding Deformable Alignment in Video Super-Resolution—0
Show:102550
← PrevPage 280 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified