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 3611–3620 of 3874 papers

TitleStatusHype
Image Super-resolution via Feature-augmented Random ForestCode0
A Frequency Domain Neural Network for Fast Image Super-resolution—0
Image Inpainting for High-Resolution Textures using CNN Texture Synthesis—0
Super-FAN: Integrated facial landmark localization and super-resolution of real-world low resolution faces in arbitrary poses with GANs—0
Deep Sampling Networks—0
InverseNet: Solving Inverse Problems with Splitting Networks—0
FSRNet: End-to-End Learning Face Super-Resolution with Facial PriorsCode0
BLADE: Filter Learning for General Purpose Computational Photography—0
Deep Image PriorCode1
Super-Resolution for Overhead Imagery Using DenseNets and Adversarial Learning—0
Show:102550
← PrevPage 362 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified