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
S2GO: Streaming Sparse Gaussian Occupancy Prediction—0
Learning normalized image densities via dual score matchingCode0
FEAT: Full-Dimensional Efficient Attention Transformer for Medical Video GenerationCode1
MARBLE: Material Recomposition and Blending in CLIP-Space—0
How to Unlock Time Series Editing? Diffusion-Driven Approach with Multi-Grained Control—0
FPSAttention: Training-Aware FP8 and Sparsity Co-Design for Fast Video Diffusion—0
SVD-Based Graph Fractional Fourier Transform on Directed Graphs and Its Application—0
DiffCAP: Diffusion-based Cumulative Adversarial Purification for Vision Language Models—0
YOND: Practical Blind Raw Image Denoising Free from Camera-Specific Data Dependency—0
A Poisson-Guided Decomposition Network for Extreme Low-Light Image Enhancement—0
Diffusion Transformer-based Universal Dose Denoising for Pencil Beam Scanning Proton Therapy—0
CHIME: Conditional Hallucination and Integrated Multi-scale Enhancement for Time Series Diffusion Model—0
Object-centric 3D Motion Field for Robot Learning from Human Videos—0
TracLLM: A Generic Framework for Attributing Long Context LLMsCode1
Magic Mushroom: A Customizable Benchmark for Fine-grained Analysis of Retrieval Noise Erosion in RAG Systems—0
Unrolling Nonconvex Graph Total Variation for Image Denoising—0
InfiniteAudio: Infinite-Length Audio Generation with Consistency—0
FreeScene: Mixed Graph Diffusion for 3D Scene Synthesis from Free Prompts—0
ADFormer: Aggregation Differential Transformer for Passenger Demand ForecastingCode0
Adaptive Differential Denoising for Respiratory Sounds ClassificationCode1
Channel-adaptive Cross-modal Generative Semantic Communication for Point Cloud Transmission—0
NTIRE 2025 the 2nd Restore Any Image Model (RAIM) in the Wild Challenge—0
ReconXF: Graph Reconstruction Attack via Public Feature Explanations on Privatized Node Features and Labels—0
Psi-Sampler: Initial Particle Sampling for SMC-Based Inference-Time Reward Alignment in Score Models—0
Synthesis of discrete-continuous quantum circuits with multimodal diffusion modelsCode2
Image Generation from Contextually-Contradictory Prompts—0
ProtInvTree: Deliberate Protein Inverse Folding with Reward-guided Tree Search—0
SkyReels-Audio: Omni Audio-Conditioned Talking Portraits in Video Diffusion TransformersCode9
Latent Wavelet Diffusion: Enabling 4K Image Synthesis for Free—0
Towards Effective and Efficient Adversarial Defense with Diffusion Models for Robust Visual TrackingCode0
A Composite Predictive-Generative Approach to Monaural Universal Speech Enhancement—0
DeGLIF for Label Noise Robust Node Classification using GNNs—0
EasyText: Controllable Diffusion Transformer for Multilingual Text RenderingCode2
ComposeAnything: Composite Object Priors for Text-to-Image Generation—0
Optimal Weighted Convolution for Classification and DenosingCode2
On Designing Diffusion Autoencoders for Efficient Generation and Representation LearningCode0
TumorGen: Boundary-Aware Tumor-Mask Synthesis with Rectified Flow Matching—0
Unleashing High-Quality Image Generation in Diffusion Sampling Using Second-Order Levenberg-Marquardt-LangevinCode1
Optimal Density Functions for Weighted Convolution in Learning ModelsCode2
RealDrive: Retrieval-Augmented Driving with Diffusion Models—0
Aligning Protein Conformation Ensemble Generation with Physical Feedback—0
STAR-Net: An Interpretable Model-Aided Network for Remote Sensing Image DenoisingCode0
Interactive Video Generation via Domain Adaptation—0
Diffusion-Based Symbolic Regression—0
Impact of Bottleneck Layers and Skip Connections on the Generalization of Linear Denoising Autoencoders—0
Composite Reward Design in PPO-Driven Adaptive FilteringCode0
ADG: Ambient Diffusion-Guided Dataset Recovery for Corruption-Robust Offline Reinforcement Learning—0
D-AR: Diffusion via Autoregressive ModelsCode2
ProDiff: Prototype-Guided Diffusion for Minimal Information Trajectory ImputationCode1
LoRAShop: Training-Free Multi-Concept Image Generation and Editing with Rectified Flow Transformers—0
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