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 651675 of 3874 papers

TitleStatusHype
Conditional Hyper-Network for Blind Super-Resolution with Multiple DegradationsCode1
Angular Super-Resolution in Diffusion MRI with a 3D Recurrent Convolutional AutoencoderCode1
A residual dense vision transformer for medical image super-resolution with segmentation-based perceptual loss fine-tuningCode1
Conditional Simulation Using Diffusion Schrödinger BridgesCode1
Conditional Variational Diffusion ModelsCode1
Cross-Resolution Flow Propagation for Foveated Video Super-ResolutionCode1
Cross-sensor super-resolution of irregularly sampled Sentinel-2 time seriesCode1
Fully 11 Convolutional Network for Lightweight Image Super-ResolutionCode1
DiffFuSR: Super-Resolution of all Sentinel-2 Multispectral Bands using Diffusion ModelsCode1
A Feature Reuse Framework with Texture-adaptive Aggregation for Reference-based Super-ResolutionCode1
Diffusion Models Beat GANs on Image ClassificationCode1
GCRDN: Global Context-Driven Residual Dense Network for Remote Sensing Image SuperresolutionCode1
Detail-Preserving Transformer for Light Field Image Super-ResolutionCode1
Deterministic Image-to-Image Translation via Denoising Brownian Bridge Models with Dual ApproximatorsCode1
GenerateCT: Text-Conditional Generation of 3D Chest CT VolumesCode1
Consistent Direct Time-of-Flight Video Depth Super-ResolutionCode1
ARM: Any-Time Super-Resolution MethodCode1
Generative Adversarial NetworksCode1
Designing a Practical Degradation Model for Deep Blind Image Super-ResolutionCode1
DEPTHOR: Depth Enhancement from a Practical Light-Weight dToF Sensor and RGB ImageCode1
DeSRA: Detect and Delete the Artifacts of GAN-based Real-World Super-Resolution ModelsCode1
DHP: Differentiable Meta Pruning via HyperNetworksCode1
GSR4B: Biomass Map Super-Resolution with Sentinel-1/2 GuidanceCode1
GSR-Net: Graph Super-Resolution Network for Predicting High-Resolution from Low-Resolution Functional Brain ConnectomesCode1
Degradation Oriented and Regularized Network for Blind Depth Super-ResolutionCode1
Show:102550
← PrevPage 27 of 155Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41Unverified