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 3601–3625 of 3874 papers

TitleStatusHype
Brain MRI Super Resolution Using 3D Deep Densely Connected Neural Networks—0
High-throughput, high-resolution registration-free generated adversarial network microscopyCode0
Joint convolutional neural pyramid for depth map super-resolution—0
Aerial Spectral Super-Resolution using Conditional Adversarial Networks—0
On the Diversity of Realistic Image SynthesisCode0
Super-Resolution with Deep Adaptive Image Resampling—0
"Zero-Shot" Super-Resolution using Deep Internal LearningCode0
Learning a Single Convolutional Super-Resolution Network for Multiple DegradationsCode0
SRPGAN: Perceptual Generative Adversarial Network for Single Image Super Resolution—0
Deep Burst DenoisingCode0
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
Video Enhancement with Task-Oriented FlowCode1
xUnit: Learning a Spatial Activation Function for Efficient Image RestorationCode0
The Perception-Distortion TradeoffCode0
Deep Inception-Residual Laplacian Pyramid Networks for Accurate Single Image Super-Resolution—0
CT-SRCNN: Cascade Trained and Trimmed Deep Convolutional Neural Networks for Image Super Resolution—0
Show:102550
← PrevPage 145 of 155Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified