Denoising

Follow this field Ask about this field

Recent momentum

emerging

0 papers in the last 28 days · 0.0% of indexed attention

Twelve weeks of publication activity for this topic as it is defined today.

Weekly history

Recent digests

What was published in this field, kept on the site without email delivery.

Period ending 2026-09-21

25 new papers

A weekly snapshot of new work published in Denoising.

Period ending 2026-09-14

22 new papers

A weekly snapshot of new work published in Denoising.

Period ending 2026-09-07

34 new papers

A weekly snapshot of new work published in Denoising.

Inside this field

Focused directions

Focused topic

Image Denoising

Within Denoising

271 papersExplore

Focused topic

Discrete Diffusion Model

Within Denoising

258 papersExplore

Focused topic

Latent Diffusion Model

Within Denoising

92 papersExplore

Focused topic

Diffusion Sampling

Within Denoising

82 papersExplore

Focused topic

Score-Based Diffusion Model

Within Denoising

56 papersExplore

Focused topic

Generative Priors

Within Denoising

54 papersExplore

Focused topic

Identity-Conditioned Latent Diffusion Models

Within Denoising

54 papersExplore

Focused topic

Diffusion Priors

Within Denoising

52 papersExplore

Focused topic

Denoising Diffusion Probabilistic Model

Within Denoising

46 papersExplore

Focused topic

Denoising Trajectory

Within Denoising

44 papersExplore

Focused topic

Reward-Guided Diffusion

Within Denoising

44 papersExplore

Focused topic

Diffusion Dynamics

Within Denoising

43 papersExplore

1,018 papers

Latest in Denoising

Browse all topics →

Diffusion Models Are Statistically Optimal for Learning Low-Dimensional Multi-Modal Distributions
May 28, 2026Jingda Wu, Changxiao CaiLow-Dimensional Structure Score-Based Diffusion Model
Native Audio-Visual Alignment for Generation
May 28, 2026Longbin Ji, Guan Wang, Xuan Wei +6Joint Audio-Video Generation Audio-Visual Consistency
Sample-Efficient Diffusion-based Reinforcement Learning with Critic Guidance
May 28, 2026Shutong Ding, Zejia Zhong, Zhongyi Wang +4Diffusion Policies Reward-Guided Diffusion
A Fully Convolutional Approach to Denoising Structural Dynamics Data from X-Ray Photon Correlation Spectroscopy
May 28, 2026Nisar Nellikunnummel, Andi Barbour, Lutz Wiegart +2X-Ray Photon Correlation Spectroscopy Image Denoising
Fisher-Preserving Guidance: Training-Free Manifold Constraints for Safe Diffusion Control
May 28, 2026Hao Ren, Zetong Bi, Yiming Zeng +5Diffusion Policies Reward-Guided Diffusion
CityGen: Structure-Guided City-Style Synthesis for Cross-City Autonomous Driving
May 28, 2026Zezhong Qian, Zhao Yang, Lu Tan +4Autonomous Driving Cross-Domain Generalization
Midpoint Generative Models
May 28, 2026Daniil Shlenskii, Nikita Gushchin, Lev Novitskiy +2Generative Models Discrete Diffusion Model
Attention as In-Context Empirical Bayes: A Two-Stage View via Particle Dynamics
May 28, 2026Matthew Smart, Soumya Ganguly, Nilava Metya +2In-Context Posterior
V2I Work Zone Geometry Reconstruction with Pose-Conditioned UWB Range Denoising
May 28, 2026Jiaxi Liu, Hangyu Li, Yang Cheng +7Geometric Reconstruction Ultra-Wideband
Trajectory Constraints for Imaging Inverse Problems
May 27, 2026Chaoyan Huang, Haijie Yuan, Saiprasad RavishankarIll-Posed Inverse Problem Inverse Problem
Orthogonal Concept Erasure for Diffusion Models
May 27, 2026Yuhao Sun, Lingyun Yu, Haoxiang Xu +3Concept Erasure Discrete Diffusion Model
DriveWAM: Video Generative Priors Enable Scalable World-Action Modeling for Autonomous Driving
May 27, 2026Chen Shi, Jinrui Xu, Shaoshuai Shi +3Video Pretraining Efficient World-Action Model
Latent Diffusion for Missing Data
May 27, 2026Alberte Heering Estad, Ignacio Peis, Jes FrellsenLatent Diffusion Model Latent Space
DenoiseRL: Bootstrapping Reasoning Models to Recover from Noisy Prefixes
May 27, 2026Caijun Xu, Changyi Xiao, Zhongyuan Peng +1Large Reasoning Models Image Denoising
PhAME: Phenotype-Aware Molecular Editing via Latent Diffusion
May 27, 2026Łukasz Janisiów, Sebastian Musiał, Bartosz Zieliński +2Molecular Optimization Drug Design
Gradient Step Plug-and-Play Model for Dental Cone-Beam CT Reconstruction
May 27, 2026Idris Tatachak, Luis Kabongo, Nicolas Papadakis +2Cone-Beam Computed Tomography Image Denoising
Geometry-Correct Diffusion Posterior Sampling with Denoiser-Pullback Curvature Guidance and Manifold-Aligned Damping
May 27, 2026Seunghyeok Shin, Minwoo Kim, Dabin Kim +1Diffusion Sampling Image Denoising
SANTS: A State-Adaptive Scheduler for World Action Models
May 27, 2026Yirui Sun, Guangyu Zhuge, Keliang Liu +4Efficient World-Action Model World Models
Residualized Temporal Sparse Autoencoders for Interpreting Diffusion Models
May 27, 2026Calvin Yeung, Prathyush Poduval, Ali Zakeri +2Image Denoising
SYNAPSE: Neuro-Symbolic Visual Thought-to-Text Decoding via Topological Semantic Denoising
May 27, 2026Akshaj Murhekar, Abhijit MishraNeuro-Symbolic Framework Geo-Contextual Alignment
From Scores to Gibbs Correctors: Accelerating Uniform-Rate Discrete Diffusion Models
May 26, 2026Yuchen Liang, Ness Shroff, Yingbin LiangDiffusion Sampling Diffusion Processes
Feedforward 3D Editing Learns from Semantic-Part Transformation
May 26, 2026Jiawei Weng, Saining Zhang, Zhenxin Diao +43D Editing 3D Generative Models
High-Quality Synthetic Financial Time-Series using a GAN-Diffusion Framework
May 26, 2026Giuseppe Masi, Andrea Coletta, Novella BartoliniSynthetic Time Series Synthetic Data
JLT: Clean-Latent Prediction in Latent Diffusion Transformers
May 26, 2026Funing Fu, Tenghui Wang, Guanyu Zhou +2Latent Diffusion Model Latent Bridge Matching
Sampling Data with Chains of Forward-Backward Diffusion Steps
May 26, 2026Hyunmo Kang, Noam Itzhak Levi, Corinna Elena Wegner +2Diffusion Sampling Phase Transitions
Learning Energy-Based Models from Stochastic Interpolants using Spatiotemporal Differences
May 26, 2026Hanlin Yu, RuiKang OuYang, Partha Kaushik +3Discrete Diffusion Model Contrastive Learning
RT-Lynx: Putting the GEMM Sparsity In a Right Way for Diffusion Models
May 26, 2026Xing Cong, Hanlin Tang, Kan Liu +3Multimodal Diffusion Transformers Sparse Expert Activation
On the Error-Correcting Effects of Stochasticity in Discrete Diffusion
May 26, 2026William Yuan, Sungwon Jeong, Amirali AghazadehDiscrete Diffusion Model Stochastic
DGLD: Domain-Gated Latent Diffusion for the Discovery of Novel Energetic Materials
May 26, 2026Yehudit Aperstein, Alexander ApartsinVast Chemical Space Molecular Structure Elucidation
Triadic Dynamics Aware Diffusion Posterior Sampling for Inverse Problems: Optimizing Guidance and Stochasticity Schedules
May 26, 2026Junseo Bang, Dong Ju Mun, Hoigi Seo +2Diffusion Sampling Posterior Sampling
OMGTex: One-stage Multi-style Facial Texture Reconstruction without Geometry Guidance
May 25, 2026Zitong Xiao, Yuda Qiu, Zisheng Ye +1Blind Face Restoration Multi-View Diffusion Model
SAFE-Diff: Scale-Aware Attention and Feature-Dispersive Diffusion with Uncertainty Estimation for Contrast-Enhanced Breast MRI Synthesis
May 25, 2026Tianyu Zhang, Xinglong Liang, Jarek van Dijk +13Medical Image Generation Magnetic Resonance Imaging
Baton: Explicit Semantic Blueprints for Joint Video-Audio Generation
May 24, 2026Shuyuan Tu, Qi Tian, Zihan Yang +9Joint Audio-Video Generation Audio Latent
Unbiased Diffusion Variational Inversion via Principled Posterior Matching
May 24, 2026Weimin Bai, Yuxuan Gu, Yifei Wang +2Ill-Posed Inverse Problem Inverse Problem
Convex-Neural RRT*: Fast and Reliable Learning-Guided Sampling for High-Quality Robot Path Planning
May 24, 2026Hichem Cheriet, Badra Khellat Kihel, Samira Chouraqui +1Robot Planning Obstacle Avoidance
Dynamic Neural Koopman Distillation for Real-Time Robot Control Using Diffusion Models
May 24, 2026Lei Zheng, Peiqi Yu, Zengqi Peng +2Diffusion Policies Robot Planning
Trajectory-Consistent Calibration for Cache-Accelerated Diffusion Models
May 24, 2026Mingyu Liang, Dingkun Xu, Jingwei XuDenoising Trajectory Image Denoising
Cross-Domain Energy-Guided Diffusion Generation for Off-Dynamics Reinforcement Learning
May 24, 2026Yu Yang, Yihong Guo, Anqi Liu +1Offline Reinforcement Learning Diffusion Policies
Leveraging pretrained RGB denoisers for hyperspectral image restoration
May 23, 2026Daniele Picone, Mohamad Jouni, Mauro Dalla-MuraHyperspectral Imaging Image Restoration
Beyond Generative Priors: Minority Sampling with JEPA-Guided Diffusion
May 23, 2026Sol Park, Soobin UmDiffusion Sampling Generative Priors
Phase-Aware Wavelet-Based-Scattering Encoder-Decoder for Dense Predictions
May 23, 2026Ghassen Marrakchi, Basarab MateiDiscrete Wavelet Transform Dense Prediction
TUBE: Tangent Upper Bound on Evidence for Discrete Diffusion Language Models
May 22, 2026Arseny Ivanov, Sergei Kholkin, Vladislav Gromadskii +3Diffusion Language Models Likelihood
PiD: Fast and High-Resolution Latent Decoding with Pixel Diffusion
May 22, 2026Yifan Lu, Qi Wu, Jay Zhangjie Wu +4Latent Diffusion Model
GenRecon: Bridging Generative Priors for Multi-View 3D Scene Reconstruction
May 22, 2026Katharina Schmid, Nicolas von Lützow, Jozef Hladký +23D Reconstruction 3D Generation
Point Tracking Improves World Action Models
May 22, 2026Jiarui Guan, Wenshuai Zhao, Yue Pei +3Efficient World-Action Model Multi-Object Tracking
Efficient One-Step Diffusion Restoration Model with Compact Token Compression and Linear Attention
May 22, 2026Bingtian Qiao, Yue Shi, Yingjie Zhou +3Generative Super-Resolution Image Restoration
Contrastive Distribution Matching for Amortized Sequential Monte Carlo in Discrete Diffusion
May 22, 2026Jaihoon Kim, Taehoon Yoon, Prin Phunyaphibarn +3Discrete Diffusion Model Monte Carlo
Discontinuous Galerkin Neural Operator for Pathology Defocus Deblurring
May 22, 2026Shaoqing Duan, Haofei Song, Xintian Mao +2Motion Blur Image Denoising
Coloring the Noise: Adversarial Sobolev Alignment for Faithful Image Super Resolution
May 22, 2026Hongbo Wang, Huaibo Huang, Pin Wang +3Generative Super-Resolution Large-Scale Image Generation
The Attribution Contract: Feature Attribution for Generative Language Models
May 21, 2026Giang NguyenGenerative Kernel Contracts
Dithering Defense: Adversarial Robustness of Vision Foundation Models via Multi-Level Floyd-Steinberg Dithering
May 21, 2026Yury Belousov, Brian Pulfer, Vitaliy Kinakh +1Vision Foundation Models Discrete Diffusion Model
Diffusion-based Denoising Beats Vanilla Score Matching in Parameter Estimation: A Theoretical Explanation
May 21, 2026Benedikt Lütke Schwienhorst, Nadja Klein, Johannes LedererScore-Based Diffusion Model Theoretical Foundations
DecQ: Detail-Condensing Queries for Enhanced Reconstruction and Generation in Representation Autoencoders
May 21, 2026Tianhang Wang, Yitong Chen, Wei Song +3Masked Autoencoders Latent Diffusion Model
Uniform Diffusion Models Revisited: Leave-One-Out Denoiser and Absorbing State Reformulation
May 21, 2026Samson Gourevitch, Yazid Janati, Dario Shariatian +4Masked Diffusion Language Models Discrete Diffusion Model
The Value of Covariance Matching in Gaussian DDPMs and the Lanczos Sampler
May 21, 2026Md Sahil Akhtar, Aymane El Gadarri, Vivek F. Farias +1Markovian Sampling Covariance Estimation
A Tutorial on Diffusion Theory: From Differential Equations to Diffusion Models
May 21, 2026Jiayi Fu, Yuxia WangDiffusion Processes Stochastic Differential Equations
Physics-Informed Generative Solver: Bridging Data-Driven Priors and Conservation Laws for Stable Spatiotemporal Field Reconstruction
May 21, 2026Ziyuan Zhu, Keyu Hu, Zhifei Chen +10Ill-Posed Inverse Problem Generative Priors
PIU: Proximity-guided Identity Unlearning in ID-Conditioned Diffusion Models
May 21, 2026Jose Edgar Hernandez Cancino Estrada, Mauro Díaz Lupone, Žiga Emeršič +3Identity-Conditioned Latent Diffusion Models Several Approximate Unlearning Strategies
Imagine2Real: Towards Zero-shot Humanoid-Object Interaction via Video Generative Priors
May 21, 2026Jiahe Chen, ZiRui Wang, Feiyu Jia +7Articulated Objects Imagination
Automatic Contextual Audio Denoising
May 21, 2026Diep Luong, Konstantinos Drossos, Mikko Heikkinen +1Image Denoising

May 28, 2026 · stat.MLJ/K move · Enter open · S save

Diffusion Models Are Statistically Optimal for Learning Low-Dimensional Multi-Modal Distributions

Jingda Wu, Changxiao Cai

Department of Industrial and Operations Engineering, University of Michigan, Ann Arbor, USA.

Score-based diffusion models have demonstrated remarkable empirical success in learning high-dimensional distributions, particularly those exhibiting low-dimensional and multi-modal structures. However, theoretical understanding of their statistical efficiency remains limited. Existing theories typically rely on strong regularity assumptions, such as uniformly bounded densities or globally smooth score functions, which fail to capture such intrinsic structures. In this work, we study the sample complexity of diffusion models for learning distributions supported on a union of low-dimensional subspaces. Assuming that the data distribution within each subspace is subgaussian, we show that diffusion models require at most

\widetilde{O}(\varepsilon^{-k \vee 2})

samples to achieve

\varepsilon

error in 1-Wasserstein distance, where

k

is the intrinsic dimension. This near-optimal convergence rate depends only on the intrinsic dimension and significantly improves upon prior theoretical guarantees that suffer from the curse of dimensionality. Notably, our analysis applies to a broad collection of distributions without imposing smoothness, bounded-density, or log-concavity assumptions. Overall, our results show that diffusion models can statistically adapt to intrinsic low-dimensional structure while naturally accommodating multi-modal data, offering a rigorous theoretical justification for their success in complex high-dimensional learning tasks.

Low-Dimensional Structure Score-Based Diffusion Model Optimal Sample Complexity Distributional Learning Sample Complexity Statistical Inference

Open paper Ask about it PDF