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 1941–1950 of 3874 papers

TitleStatusHype
Dense Dual-Attention Network for Light Field Image Super-Resolution—0
Densely Connected High Order Residual Network for Single Frame Image Super Resolution—0
Dense U-net for super-resolution with shuffle pooling layer—0
Depth Anything with Any Prior—0
Depth Separable architecture for Sentinel-5P Super-Resolution—0
Depth Super Resolution by Rigid Body Self-Similarity in 3D—0
Depth Super-Resolution from Explicit and Implicit High-Frequency Features—0
DepthwiseGANs: Fast Training Generative Adversarial Networks for Realistic Image Synthesis—0
Designing A Composite Dictionary Adaptively From Joint Examples—0
Detailed 3D Human Body Reconstruction from Multi-view Images Combining Voxel Super-Resolution and Learned Implicit Representation—0
Show:102550
← PrevPage 195 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified