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 321–330 of 3874 papers

TitleStatusHype
CHIMLE: Conditional Hierarchical IMLE for Multimodal Conditional Image SynthesisCode1
Compiler-Aware Neural Architecture Search for On-Mobile Real-time Super-ResolutionCode1
Discovering Distinctive "Semantics" in Super-Resolution NetworksCode1
Discrete Cosine Transform Network for Guided Depth Map Super-ResolutionCode1
Diffusion Models Beat GANs on Image ClassificationCode1
Diffusion Model Based Posterior Sampling for Noisy Linear Inverse ProblemsCode1
Cascaded Temporal Updating Network for Efficient Video Super-ResolutionCode1
Catch-A-Waveform: Learning to Generate Audio from a Single Short ExampleCode1
Resolution Enhancement Processing on Low Quality Images Using Swin Transformer Based on Interval Dense Connection StrategyCode1
Diffusion-based Blind Text Image Super-ResolutionCode1
Show:102550
← PrevPage 33 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified