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 1–50 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
GLEAN: Generative Latent Bank for Image Super-Resolution and BeyondCode5
Pixel-level and Semantic-level Adjustable Super-resolution: A Dual-LoRA ApproachCode4
Adversarial Diffusion Compression for Real-World Image Super-ResolutionCode4
One-Step Effective Diffusion Network for Real-World Image Super-ResolutionCode4
Flash Diffusion: Accelerating Any Conditional Diffusion Model for Few Steps Image GenerationCode4
A Survey on Visual MambaCode4
SeeSR: Towards Semantics-Aware Real-World Image Super-ResolutionCode4
DiffBIR: Towards Blind Image Restoration with Generative Diffusion PriorCode4
Exploiting Diffusion Prior for Real-World Image Super-ResolutionCode4
Zero-Shot Image Restoration Using Denoising Diffusion Null-Space ModelCode4
EfficientViT: Multi-Scale Linear Attention for High-Resolution Dense PredictionCode4
NAFSSR: Stereo Image Super-Resolution Using NAFNetCode4
High-Resolution Image Synthesis with Latent Diffusion ModelsCode4
Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic DataCode4
Event-Enhanced Blurry Video Super-ResolutionCode3
The Tenth NTIRE 2025 Efficient Super-Resolution Challenge ReportCode3
CATANet: Efficient Content-Aware Token Aggregation for Lightweight Image Super-ResolutionCode3
One Diffusion Step to Real-World Super-Resolution via Flow Trajectory DistillationCode3
TSD-SR: One-Step Diffusion with Target Score Distillation for Real-World Image Super-ResolutionCode3
General Geospatial Inference with a Population Dynamics Foundation ModelCode3
Degradation-Guided One-Step Image Super-Resolution with Diffusion PriorsCode3
Panacea+: Panoramic and Controllable Video Generation for Autonomous DrivingCode3
Blind Image Restoration via Fast Diffusion InversionCode3
Inf-DiT: Upsampling Any-Resolution Image with Memory-Efficient Diffusion TransformerCode3
Real-Time 4K Super-Resolution of Compressed AVIF Images. AIS 2024 Challenge SurveyCode3
The Ninth NTIRE 2024 Efficient Super-Resolution Challenge ReportCode3
DRCT: Saving Image Super-resolution away from Information BottleneckCode3
VmambaIR: Visual State Space Model for Image RestorationCode3
CAMixerSR: Only Details Need More "Attention"Code3
Lumiere: A Space-Time Diffusion Model for Video GenerationCode3
Upscale-A-Video: Temporal-Consistent Diffusion Model for Real-World Video Super-ResolutionCode3
HierSpeech++: Bridging the Gap between Semantic and Acoustic Representation of Speech by Hierarchical Variational Inference for Zero-shot Speech SynthesisCode3
AudioSR: Versatile Audio Super-resolution at ScaleCode3
HAT: Hybrid Attention Transformer for Image RestorationCode3
Pixel-Aware Stable Diffusion for Realistic Image Super-resolution and Personalized StylizationCode3
ResShift: Efficient Diffusion Model for Image Super-resolution by Residual ShiftingCode3
MedSegDiff: Medical Image Segmentation with Diffusion Probabilistic ModelCode3
Activating More Pixels in Image Super-Resolution TransformerCode3
A new face swap method for image and video domains: a technical reportCode3
VRT: A Video Restoration TransformerCode3
Show:102550
← PrevPage 1 of 78Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified