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 341–350 of 3874 papers

TitleStatusHype
ECAMP: Entity-centered Context-aware Medical Vision Language Pre-trainingCode1
Scale-Equivariant Imaging: Self-Supervised Learning for Image Super-Resolution and DeblurringCode1
Image Restoration Through Generalized Ornstein-Uhlenbeck BridgeCode1
TMP: Temporal Motion Propagation for Online Video Super-ResolutionCode1
Diffusion-based Blind Text Image Super-ResolutionCode1
Semantic Lens: Instance-Centric Semantic Alignment for Video Super-ResolutionCode1
TULIP: Transformer for Upsampling of LiDAR Point CloudsCode1
SGNet: Structure Guided Network via Gradient-Frequency Awareness for Depth Map Super-ResolutionCode1
Iterative Token Evaluation and Refinement for Real-World Super-ResolutionCode1
Training Neural Networks on RAW and HDR Images for Restoration TasksCode1
Show:102550
← PrevPage 35 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified