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 1271–1280 of 3874 papers

TitleStatusHype
Cross-Resolution Learning for Face RecognitionCode0
Maintaining Natural Image Statistics with the Contextual LossCode0
CrossNet: An End-to-end Reference-based Super Resolution Network using Cross-scale WarpingCode0
Efficient Model-Based Deep Learning via Network Pruning and Fine-TuningCode0
L-MAGIC: Language Model Assisted Generation of Images with CoherenceCode0
Cross-domain heterogeneous residual network for single image super-resolutionCode0
ASteISR: Adapting Single Image Super-resolution Pre-trained Model for Efficient Stereo Image Super-resolutionCode0
Criteria Comparative Learning for Real-scene Image Super-ResolutionCode0
A GAN-Enhanced Deep Learning Framework for Rooftop Detection from Historical Aerial ImageryCode0
Lightweight Image Super-Resolution with Adaptive Weighted Learning NetworkCode0
Show:102550
← PrevPage 128 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified