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 571–580 of 3874 papers

TitleStatusHype
Cascaded Local Implicit Transformer for Arbitrary-Scale Super-ResolutionCode1
3D Human Pose, Shape and Texture from Low-Resolution Images and VideosCode1
Cross-Resolution Flow Propagation for Foveated Video Super-ResolutionCode1
Gated Multi-Resolution Transfer Network for Burst Restoration and EnhancementCode1
Advancing High-Resolution Video-Language Representation with Large-Scale Video TranscriptionsCode1
CVAE-GAN: Fine-Grained Image Generation through Asymmetric TrainingCode1
Cylin-Painting: Seamless 360 Panoramic Image Outpainting and BeyondCode1
D2C-SR: A Divergence to Convergence Approach for Real-World Image Super-ResolutionCode1
3D Human Shape and Pose from a Single Low-Resolution Image with Self-Supervised LearningCode1
Generalized Real-World Super-Resolution through Adversarial RobustnessCode1
Show:102550
← PrevPage 58 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified