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 2441–2450 of 3874 papers

TitleStatusHype
UDC: Unified DNAS for Compressible TinyML Models—0
Neural Architecture Search for Image Super-Resolution Using Densely Constructed Search Space: DeCoNAS—0
Neural Architecture Search for Intel Movidius VPU—0
Neural Differential Equations for Single Image Super-resolution—0
Neural Enhancement in Content Delivery Systems: The State-of-the-Art and Future Directions—0
Competition-based Adaptive ReLU for Deep Neural Networks—0
Compensation based Dictionary Transfer for Similar Multispectral Image Spectral Super-resolution—0
Neural Knitworks: Patched Neural Implicit Representation Networks—0
UG^2: a Video Benchmark for Assessing the Impact of Image Restoration and Enhancement on Automatic Visual Recognition—0
Neural Network-Inspired Analog-to-Digital Conversion to Achieve Super-Resolution with Low-Precision RRAM Devices—0
Show:102550
← PrevPage 245 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified