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 3841–3850 of 3874 papers

TitleStatusHype
AFFIRM: Affinity Fusion-based Framework for Iteratively Random Motion correction of multi-slice fetal brain MRICode0
Scene Text Telescope: Text-Focused Scene Image Super-ResolutionCode0
SCINet: Spatial and Contrast Interactive Super-Resolution Assisted Infrared UAV Target DetectionCode0
Adversarial Feedback LoopCode0
Deep Laplacian Pyramid Network for Text Images Super-ResolutionCode0
SDAN: Squared Deformable Alignment Network for Learning Misaligned Optical ZoomCode0
Fast Samplers for Inverse Problems in Iterative Refinement ModelsCode0
SDT-DCSCN for Simultaneous Super-Resolution and Deblurring of Text ImagesCode0
Fast Omni-Directional Image Super-Resolution: Adapting the Implicit Image Function with Pixel and Semantic-Wise Spherical Geometric PriorsCode0
Fast Image Restoration With Multi-Bin Trainable Linear UnitsCode0
Show:102550
← PrevPage 385 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified