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 61–70 of 3874 papers

TitleStatusHype
NTIRE 2025 Challenge on Image Super-Resolution (4): Methods and ResultsCode2
Distillation-Supervised Convolutional Low-Rank Adaptation for Efficient Image Super-ResolutionCode2
ILLUME+: Illuminating Unified MLLM with Dual Visual Tokenization and Diffusion RefinementCode2
Progressive Focused Transformer for Single Image Super-ResolutionCode2
Toward Generalized Image Quality Assessment: Relaxing the Perfect Reference Quality AssumptionCode2
Perceive, Understand and Restore: Real-World Image Super-Resolution with Autoregressive Multimodal Generative ModelsCode2
Emulating Self-attention with Convolution for Efficient Image Super-ResolutionCode2
AutoLUT: LUT-Based Image Super-Resolution with Automatic Sampling and Adaptive Residual LearningCode2
DifIISR: A Diffusion Model with Gradient Guidance for Infrared Image Super-ResolutionCode2
Geodesic Diffusion Models for Medical Image-to-Image GenerationCode2
Show:102550
← PrevPage 7 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified