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 981–990 of 3874 papers

TitleStatusHype
Frequency-Time Diffusion with Neural Cellular Automata—0
TriNeRFLet: A Wavelet Based Triplane NeRF Representation—0
Transforming Image Super-Resolution: A ConvFormer-based Efficient ApproachCode2
FMA-Net: Flow-Guided Dynamic Filtering and Iterative Feature Refinement with Multi-Attention for Joint Video Super-Resolution and Deblurring—0
AGG: Amortized Generative 3D Gaussians for Single Image to 3D—0
Super-resolution multi-contrast unbiased eye atlases with deep probabilistic refinement—0
Predicting Future States with Spatial Point Processes in Single Molecule Resolution Spatial Transcriptomics—0
What You See is What You GAN: Rendering Every Pixel for High-Fidelity Geometry in 3D GANs—0
Efficient Hybrid Zoom using Camera Fusion on Mobile Phones—0
Noise-NeRF: Hide Information in Neural Radiance Fields using Trainable Noise—0
Show:102550
← PrevPage 99 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified