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 1241–1250 of 3874 papers

TitleStatusHype
Dual-domain Modulation Network for Lightweight Image Super-Resolution—0
SASNet: Spatially-Adaptive Sinusoidal Neural Networks—0
SuperCarver: Texture-Consistent 3D Geometry Super-Resolution for High-Fidelity Surface Detail Generation—0
Resolution Invariant Autoencoder—0
Feature Alignment with Equivariant Convolutions for Burst Image Super-Resolution—0
Reconstruct Anything Model: a lightweight foundation model for computational imaging—0
Over-the-Air Time-Frequency Synchronization in Distributed ISAC Systems—0
QUIET-SR: Quantum Image Enhancement Transformer for Single Image Super-Resolution—0
Boosting Diffusion-Based Text Image Super-Resolution Model Towards Generalized Real-World Scenarios—0
AdaptSR: Low-Rank Adaptation for Efficient and Scalable Real-World Super-Resolution—0
Show:102550
← PrevPage 125 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified