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 3821–3830 of 3874 papers

TitleStatusHype
SARN: Structurally-Aware Recurrent Network for Spatio-Temporal DisaggregationCode0
Texture-enhanced Light Field Super-resolution with Spatio-Angular Decomposition KernelsCode0
A Fully Progressive Approach to Single-Image Super-ResolutionCode0
Deep Laplacian Pyramid Networks for Fast and Accurate Super-ResolutionCode0
Two-Stream Action Recognition-Oriented Video Super-ResolutionCode0
Feedback Network for Image Super-ResolutionCode0
AFN: Attentional Feedback Network based 3D Terrain Super-ResolutionCode0
TGAN: Deep Tensor Generative Adversarial Nets for Large Image GenerationCode0
Feature Forwarding for Efficient Single Image DehazingCode0
Constraint matrix factorization for space variant PSFs field restorationCode0
Show:102550
← PrevPage 383 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified