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 2071–2080 of 3874 papers

TitleStatusHype
MR Image Denoising and Super-Resolution Using Regularized Reverse Diffusion—0
Increasing the accuracy and resolution of precipitation forecasts using deep generative modelsCode1
Adaptive Patch Exiting for Scalable Single Image Super-ResolutionCode1
ARM: Any-Time Super-Resolution MethodCode1
Optical Flow for Video Super-Resolution: A Survey—0
SDOA-Net: An Efficient Deep Learning-Based DOA Estimation Network for Imperfect ArrayCode1
HIPA: Hierarchical Patch Transformer for Single Image Super Resolution—0
A Text Attention Network for Spatial Deformation Robust Scene Text Image Super-resolutionCode1
Frequency-Selective Mesh-to-Mesh Resampling for Color Upsampling of Point Clouds—0
Details or Artifacts: A Locally Discriminative Learning Approach to Realistic Image Super-ResolutionCode2
Show:102550
← PrevPage 208 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified