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

Showing 3140 of 3874 papers

TitleStatusHype
Degradation-Guided One-Step Image Super-Resolution with Diffusion PriorsCode3
Panacea+: Panoramic and Controllable Video Generation for Autonomous DrivingCode3
Blind Image Restoration via Fast Diffusion InversionCode3
Inf-DiT: Upsampling Any-Resolution Image with Memory-Efficient Diffusion TransformerCode3
Real-Time 4K Super-Resolution of Compressed AVIF Images. AIS 2024 Challenge SurveyCode3
The Ninth NTIRE 2024 Efficient Super-Resolution Challenge ReportCode3
DRCT: Saving Image Super-resolution away from Information BottleneckCode3
VmambaIR: Visual State Space Model for Image RestorationCode3
CAMixerSR: Only Details Need More "Attention"Code3
Lumiere: A Space-Time Diffusion Model for Video GenerationCode3
Show:102550
← PrevPage 4 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41Unverified