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 2001–2010 of 3874 papers

TitleStatusHype
Adaptive Dropout: Unleashing Dropout across Layers for Generalizable Image Super-Resolution—0
Deep machine learning-assisted multiphoton microscopy to reduce light exposure and expedite imaging—0
Deeply Supervised Depth Map Super-Resolution as Novel View Synthesis—0
Learned Multi-View Texture Super-Resolution—0
Deeply Matting-based Dual Generative Adversarial Network for Image and Document Label Supervision—0
Learned super resolution ultrasound for improved breast lesion characterization—0
Learn From Orientation Prior for Radiograph Super-Resolution: Orientation Operator Transformer—0
Deeply Aggregated Alternating Minimization for Image Restoration—0
Learning A 3D-CNN and Transformer Prior for Hyperspectral Image Super-Resolution—0
Towards Real-world Video Face Restoration: A New Benchmark—0
Show:102550
← PrevPage 201 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified