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 931–940 of 3874 papers

TitleStatusHype
Hyperspectral Image Super-resolution via Deep Progressive Zero-centric Residual LearningCode1
Exploring Sparsity in Image Super-Resolution for Efficient InferenceCode1
AutoGAN-Distiller: Searching to Compress Generative Adversarial NetworksCode1
iSeeBetter: Spatio-temporal video super-resolution using recurrent generative back-projection networksCode1
Super-resolution Variational Auto-EncodersCode1
Neural Sparse Representation for Image RestorationCode1
Learning Texture Transformer Network for Image Super-ResolutionCode1
Image Super-Resolution with Cross-Scale Non-Local Attention and Exhaustive Self-Exemplars MiningCode1
TDAN: Temporally-Deformable Alignment Network for Video Super-ResolutionCode1
Joint Demosaicing and Denoising With Self GuidanceCode1
Show:102550
← PrevPage 94 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified