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 151–200 of 7282 papers

TitleStatusHype
Faster Diffusion: Rethinking the Role of the Encoder for Diffusion Model InferenceCode2
Fast Training of Diffusion Models with Masked TransformersCode2
FlowDiffuser: Advancing Optical Flow Estimation with Diffusion ModelsCode2
FORA: Fast-Forward Caching in Diffusion Transformer AccelerationCode2
Be Yourself: Bounded Attention for Multi-Subject Text-to-Image GenerationCode2
FastComposer: Tuning-Free Multi-Subject Image Generation with Localized AttentionCode2
EZIGen: Enhancing zero-shot personalized image generation with precise subject encoding and decoupled guidanceCode2
Beyond Text: Frozen Large Language Models in Visual Signal ComprehensionCode2
ExT5: Towards Extreme Multi-Task Scaling for Transfer LearningCode2
Fast-DDPM: Fast Denoising Diffusion Probabilistic Models for Medical Image-to-Image GenerationCode2
Efficient Diffusion Transformer Policies with Mixture of Expert Denoisers for Multitask LearningCode2
EasyText: Controllable Diffusion Transformer for Multilingual Text RenderingCode2
Edicho: Consistent Image Editing in the WildCode2
DynamiCtrl: Rethinking the Basic Structure and the Role of Text for High-quality Human Image AnimationCode2
Adaptive Guidance: Training-free Acceleration of Conditional Diffusion ModelsCode2
Dual-domain strip attention for image restorationCode2
EAMamba: Efficient All-Around Vision State Space Model for Image RestorationCode2
FastDiff: A Fast Conditional Diffusion Model for High-Quality Speech SynthesisCode2
FRAG: Frequency Adapting Group for Diffusion Video EditingCode2
GLAD: Towards Better Reconstruction with Global and Local Adaptive Diffusion Models for Unsupervised Anomaly DetectionCode2
DPOT: Auto-Regressive Denoising Operator Transformer for Large-Scale PDE Pre-TrainingCode2
DnLUT: Ultra-Efficient Color Image Denoising via Channel-Aware Lookup TablesCode2
Drag Your Noise: Interactive Point-based Editing via Diffusion Semantic PropagationCode2
DiT-3D: Exploring Plain Diffusion Transformers for 3D Shape GenerationCode2
AdaPoinTr: Diverse Point Cloud Completion with Adaptive Geometry-Aware TransformersCode2
Dita: Scaling Diffusion Transformer for Generalist Vision-Language-Action PolicyCode2
Dreamer XL: Towards High-Resolution Text-to-3D Generation via Trajectory Score MatchingCode2
DIFUSCO: Graph-based Diffusion Solvers for Combinatorial OptimizationCode2
DiGress: Discrete Denoising diffusion for graph generationCode2
Diffusion Transformer PolicyCode2
A Simple and Model-Free Path Filtering Algorithm for Smoothing and AccuracyCode2
Diffusion Recommender ModelCode2
Diffusion-Sharpening: Fine-tuning Diffusion Models with Denoising Trajectory SharpeningCode2
Diffusion Prior-Based Amortized Variational Inference for Noisy Inverse ProblemsCode2
Augraphy: A Data Augmentation Library for Document ImagesCode2
Discrete Diffusion Modeling by Estimating the Ratios of the Data DistributionCode2
dKV-Cache: The Cache for Diffusion Language ModelsCode2
Diffusion Probabilistic Models beat GANs on Medical ImagesCode2
DocDiff: Document Enhancement via Residual Diffusion ModelsCode2
DPoser: Diffusion Model as Robust 3D Human Pose PriorCode2
DiffusionTrack: Diffusion Model For Multi-Object TrackingCode2
DualDn: Dual-domain Denoising via Differentiable ISPCode2
Ray Denoising: Depth-aware Hard Negative Sampling for Multi-view 3D Object DetectionCode2
Dynamic Pre-training: Towards Efficient and Scalable All-in-One Image RestorationCode2
DiSA: Diffusion Step Annealing in Autoregressive Image GenerationCode2
EchoScene: Indoor Scene Generation via Information Echo over Scene Graph DiffusionCode2
EDICT: Exact Diffusion Inversion via Coupled TransformationsCode2
Effective Cloud Removal for Remote Sensing Images by an Improved Mean-Reverting Denoising Model with Elucidated Design SpaceCode2
Diffusion models as plug-and-play priorsCode2
Diffusion Models and Representation Learning: A SurveyCode2
Show:102550
← PrevPage 4 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