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

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 101–150 of 7282 papers

TitleStatusHype
3D-Adapter: Geometry-Consistent Multi-View Diffusion for High-Quality 3D GenerationCode3
MotionFollower: Editing Video Motion via Lightweight Score-Guided DiffusionCode3
MAXIM: Multi-Axis MLP for Image ProcessingCode3
Visual Style Prompting with Swapping Self-AttentionCode3
Make-Your-Anchor: A Diffusion-based 2D Avatar Generation FrameworkCode3
ModelScope Text-to-Video Technical ReportCode3
Instruct-IPT: All-in-One Image Processing Transformer via Weight ModulationCode3
Improved Denoising Diffusion Probabilistic ModelsCode3
LinFusion: 1 GPU, 1 Minute, 16K ImageCode3
AdaIR: Adaptive All-in-One Image Restoration via Frequency Mining and ModulationCode3
HAT: Hybrid Attention Transformer for Image RestorationCode3
High-Resolution Image Reconstruction With Latent Diffusion Models From Human Brain ActivityCode3
Image Quality Assessment for Magnetic Resonance ImagingCode3
Free4D: Tuning-free 4D Scene Generation with Spatial-Temporal ConsistencyCode3
FreeU: Free Lunch in Diffusion U-NetCode3
Generalizing Denoising to Non-Equilibrium Structures Improves Equivariant Force FieldsCode3
AnyTop: Character Animation Diffusion with Any TopologyCode3
GoalFlow: Goal-Driven Flow Matching for Multimodal Trajectories Generation in End-to-End Autonomous DrivingCode3
Optimal Stepsize for Diffusion SamplingCode3
DreamMatcher: Appearance Matching Self-Attention for Semantically-Consistent Text-to-Image PersonalizationCode2
Dreamer XL: Towards High-Resolution Text-to-3D Generation via Trajectory Score MatchingCode2
BAMM: Bidirectional Autoregressive Motion ModelCode2
Towards Stabilized and Efficient Diffusion Transformers through Long-Skip-Connections with Spectral ConstraintsCode2
Aligning Text-to-Image Diffusion Models with Reward BackpropagationCode2
3D Human Mesh Estimation from Virtual MarkersCode2
All-In-One Medical Image Restoration via Task-Adaptive RoutingCode2
DPOT: Auto-Regressive Denoising Operator Transformer for Large-Scale PDE Pre-TrainingCode2
DocDiff: Document Enhancement via Residual Diffusion ModelsCode2
DPoser: Diffusion Model as Robust 3D Human Pose PriorCode2
Drag Your Noise: Interactive Point-based Editing via Diffusion Semantic PropagationCode2
DualDn: Dual-domain Denoising via Differentiable ISPCode2
AlexaTM 20B: Few-Shot Learning Using a Large-Scale Multilingual Seq2Seq ModelCode2
dKV-Cache: The Cache for Diffusion Language ModelsCode2
DiT-3D: Exploring Plain Diffusion Transformers for 3D Shape GenerationCode2
Discrete Diffusion Modeling by Estimating the Ratios of the Data DistributionCode2
Dita: Scaling Diffusion Transformer for Generalist Vision-Language-Action PolicyCode2
DiGress: Discrete Denoising diffusion for graph generationCode2
DiSA: Diffusion Step Annealing in Autoregressive Image GenerationCode2
Diffusion Transformer PolicyCode2
DIFUSCO: Graph-based Diffusion Solvers for Combinatorial OptimizationCode2
DnLUT: Ultra-Efficient Color Image Denoising via Channel-Aware Lookup TablesCode2
Dual-domain strip attention for image restorationCode2
Spatio-Temporal Few-Shot Learning via Diffusive Neural Network GenerationCode2
Diffusion Probabilistic Models beat GANs on Medical ImagesCode2
A Geometric Perspective on Diffusion ModelsCode2
Diffusion Predictive Control with ConstraintsCode2
Diffusion Prior-Based Amortized Variational Inference for Noisy Inverse ProblemsCode2
Diffusion Recommender ModelCode2
AEROBLADE: Training-Free Detection of Latent Diffusion Images Using Autoencoder Reconstruction ErrorCode2
Augraphy: A Data Augmentation Library for Document ImagesCode2
Show:102550
← PrevPage 3 of 146Next →
All datasetsDarmstadt Noise DatasetDIV2KDNDiris

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1SINDyPSNR81—Unverified
2Pixel-shuffling DownsamplingPSNR38.4—Unverified
3TWSCPSNR37.93—Unverified
4CBDNet(Syn)PSNR37.57—Unverified
5MCWNNMPSNR37.38—Unverified
6Han et alPSNR35.95—Unverified
7FFDNetPSNR34.4—Unverified
8TNRDPSNR33.65—Unverified
9CDnCNN-BPSNR32.43—Unverified
10NLRNPSNR30.8—Unverified
#ModelMetricClaimedVerifiedStatus
1DRUnet_Poisson_0.01Average PSNR (dB)33.92—Unverified
#ModelMetricClaimedVerifiedStatus
1DRANetAverage PSNR39.64—Unverified
#ModelMetricClaimedVerifiedStatus
1PCNN+RL+HMEAverage84.61—Unverified