SOTAVerified

Denoising

Denoising is a task in image processing and computer vision that aims to remove or reduce noise from an image. Noise can be introduced into an image due to various reasons, such as camera sensor limitations, lighting conditions, and compression artifacts. The goal of denoising is to recover the original image, which is considered to be noise-free, from a noisy observation.

( Image credit: Beyond a Gaussian Denoiser )

Papers

Showing 51100 of 7282 papers

TitleStatusHype
PharMolixFM: All-Atom Foundation Models for Molecular Modeling and GenerationCode4
Diffusion Models for Medical Image Analysis: A Comprehensive SurveyCode4
Adversarial Diffusion Compression for Real-World Image Super-ResolutionCode4
Scaling Diffusion Models to Real-World 3D LiDAR Scene CompletionCode3
3D Diffuser Actor: Policy Diffusion with 3D Scene RepresentationsCode3
Scaling Diffusion Transformers to 16 Billion ParametersCode3
3D Diffuser Actor: Policy Diffusion with 3D Scene RepresentationsCode3
Proxy Denoising for Source-Free Domain AdaptationCode3
ReNoise: Real Image Inversion Through Iterative NoisingCode3
Score-Guided Diffusion for 3D Human RecoveryCode3
Reservoir History Matching of the Norne field with generative exotic priors and a coupled Mixture of Experts -- Physics Informed Neural Operator Forward ModelCode3
RoHM: Robust Human Motion Reconstruction via DiffusionCode3
PixelHacker: Image Inpainting with Structural and Semantic ConsistencyCode3
Physics-Informed Diffusion ModelsCode3
Planning with Diffusion for Flexible Behavior SynthesisCode3
Denoising Vision TransformersCode3
Optimal Stepsize for Diffusion SamplingCode3
ProDiff: Progressive Fast Diffusion Model For High-Quality Text-to-SpeechCode3
3D-Adapter: Geometry-Consistent Multi-View Diffusion for High-Quality 3D GenerationCode3
On the Trajectory Regularity of ODE-based Diffusion SamplingCode3
On Distillation of Guided Diffusion ModelsCode3
MVSplat360: Feed-Forward 360 Scene Synthesis from Sparse ViewsCode3
ONE-PEACE: Exploring One General Representation Model Toward Unlimited ModalitiesCode3
Seamless Human Motion Composition with Blended Positional EncodingsCode3
MAXIM: Multi-Axis MLP for Image ProcessingCode3
DDT: Decoupled Diffusion TransformerCode3
ModelScope Text-to-Video Technical ReportCode3
Advanced Video Inpainting Using Optical Flow-Guided Efficient DiffusionCode3
LinFusion: 1 GPU, 1 Minute, 16K ImageCode3
Make-Your-Anchor: A Diffusion-based 2D Avatar Generation FrameworkCode3
Instruct-IPT: All-in-One Image Processing Transformer via Weight ModulationCode3
Image Quality Assessment for Magnetic Resonance ImagingCode3
Improved Denoising Diffusion Probabilistic ModelsCode3
Inversion-Free Image Editing with Language-Guided Diffusion ModelsCode3
HAT: Hybrid Attention Transformer for Image RestorationCode3
High-Resolution Image Reconstruction With Latent Diffusion Models From Human Brain ActivityCode3
Generalizing Denoising to Non-Equilibrium Structures Improves Equivariant Force FieldsCode3
GoalFlow: Goal-Driven Flow Matching for Multimodal Trajectories Generation in End-to-End Autonomous DrivingCode3
MotionFollower: Editing Video Motion via Lightweight Score-Guided DiffusionCode3
Free4D: Tuning-free 4D Scene Generation with Spatial-Temporal ConsistencyCode3
AdaIR: Adaptive All-in-One Image Restoration via Frequency Mining and ModulationCode3
FreeU: Free Lunch in Diffusion U-NetCode3
DreamTalk: When Emotional Talking Head Generation Meets Diffusion Probabilistic ModelsCode3
Discrete Diffusion in Large Language and Multimodal Models: A SurveyCode3
dLLM-Cache: Accelerating Diffusion Large Language Models with Adaptive CachingCode3
Attention Distillation: A Unified Approach to Visual Characteristics TransferCode3
Around the World in 80 Timesteps: A Generative Approach to Global Visual GeolocationCode3
Diffusion Models are Evolutionary AlgorithmsCode3
Diffusion-TS: Interpretable Diffusion for General Time Series GenerationCode3
AnyTop: Character Animation Diffusion with Any TopologyCode3
Show:102550
← PrevPage 2 of 146Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1SINDyPSNR81Unverified
2Pixel-shuffling DownsamplingPSNR38.4Unverified
3TWSCPSNR37.93Unverified
4CBDNet(Syn)PSNR37.57Unverified
5MCWNNMPSNR37.38Unverified
6Han et alPSNR35.95Unverified
7FFDNetPSNR34.4Unverified
8TNRDPSNR33.65Unverified
9CDnCNN-BPSNR32.43Unverified
10NLRNPSNR30.8Unverified
#ModelMetricClaimedVerifiedStatus
1DRUnet_Poisson_0.01Average PSNR (dB)33.92Unverified
#ModelMetricClaimedVerifiedStatus
1DRANetAverage PSNR39.64Unverified
#ModelMetricClaimedVerifiedStatus
1PCNN+RL+HMEAverage84.61Unverified