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 1471–1480 of 3874 papers

TitleStatusHype
Efficient Light Field Reconstruction via Spatio-Angular Dense NetworkCode0
Implicit Neural Representations for Simultaneous Reduction and Continuous Reconstruction of Multi-Altitude Climate DataCode0
Efficient Integer-Arithmetic-Only Convolutional Neural NetworksCode0
Efficient Image Super-Resolution with Feature Interaction Weighted Hybrid NetworkCode0
A Novel End-To-End Network for Reconstruction of Non-Regularly Sampled Image Data Using Locally Fully Connected LayersCode0
Implicit Image-to-Image Schrodinger Bridge for Image RestorationCode0
Improved Pothole Detection Using YOLOv7 and ESRGANCode0
Efficient Event Stream Super-Resolution with Recursive Multi-Branch FusionCode0
cGANs with Projection DiscriminatorCode0
Image Super-Resolution via RL-CSC: When Residual Learning Meets Convolutional Sparse CodingCode0
Show:102550
← PrevPage 148 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified