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 781–790 of 3874 papers

TitleStatusHype
Feedback Network for Mutually Boosted Stereo Image Super-Resolution and Disparity EstimationCode1
CTSpine1K: A Large-Scale Dataset for Spinal Vertebrae Segmentation in Computed TomographyCode1
SNIPS: Solving Noisy Inverse Problems StochasticallyCode1
Beyond the Spectrum: Detecting Deepfakes via Re-SynthesisCode1
Permutation invariance and uncertainty in multitemporal image super-resolutionCode1
Towards Compact Single Image Super-Resolution via Contrastive Self-distillationCode1
MIASSR: An Approach for Medical Image Arbitrary Scale Super-ResolutionCode1
Extremely Lightweight Quantization Robust Real-Time Single-Image Super Resolution for Mobile DevicesCode1
LAPAR: Linearly-Assembled Pixel-Adaptive Regression Network for Single Image Super-Resolution and BeyondCode1
Anchor-based Plain Net for Mobile Image Super-ResolutionCode1
Show:102550
← PrevPage 79 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified