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 1–10 of 3874 papers

TitleStatusHype
M&M VTO: Multi-Garment Virtual Try-On and EditingCode7
InspireMusic: Integrating Super Resolution and Large Language Model for High-Fidelity Long-Form Music GenerationCode5
Arbitrary-steps Image Super-resolution via Diffusion InversionCode5
EvTexture: Event-driven Texture Enhancement for Video Super-ResolutionCode5
FeatUp: A Model-Agnostic Framework for Features at Any ResolutionCode5
Efficient Diffusion Model for Image Restoration by Residual ShiftingCode5
CogView3: Finer and Faster Text-to-Image Generation via Relay DiffusionCode5
APISR: Anime Production Inspired Real-World Anime Super-ResolutionCode5
Real3D-Portrait: One-shot Realistic 3D Talking Portrait SynthesisCode5
Consistency ModelsCode5
Show:102550
← PrevPage 1 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified