Skip to content

Latest commit

 

History

History
426 lines (422 loc) · 63.5 KB

README.md

File metadata and controls

426 lines (422 loc) · 63.5 KB
Raw

Diffusion Models in Vision: A Survey (accepted at IEEE TPAMI 2023)

Denoising diffusion models represent a recent emerging topic in computer vision, demonstrating remarkable results in the area of generative modeling. A diffusion model is a deep generative model that is based on two stages, a forward diffusion stage and a reverse diffusion stage. In the forward diffusion stage, the input data is gradually perturbed over several steps by adding Gaussian noise. In the reverse stage, a model is tasked at recovering the original input data by learning to gradually reverse the diffusion process, step by step. Diffusion models are widely appreciated for the quality and diversity of the generated samples, despite their known computational burdens, i.e. low speeds due to the high number of steps involved during sampling. This repository categorizes the papers about diffusion models, applied in computer vision, according to their target task. The classifcation is based on our survey Diffusion Models in Vision: A Survey, which was accepted for publication in IEEE TPAMI.

Summary

  1. Unconditional Generation
  2. Conditional Generation
  3. Text-to-Image generation
  4. Super-Resolution
  5. Image Editing
  6. Region Image Editing
  7. Inpainting
  8. Image-to-Image Translation
  9. Image Segmentation
  10. Multi-Task
  11. Medical Image-to-Image Translation
  12. Medical Image Generation
  13. Medical Image Segmentation
  14. Medical Image Anomaly Detection
  15. Video Generation
  16. Few-Shot Image Generation
  17. Counterfactual Explanations and Estimations
  18. Image Restoration
  19. Image Registration
  20. Adversarial Purification
  21. Semantic Image Generation
  22. Shape Generation and Completion
  23. Classification
  24. Point Cloud Generation
  25. Theoretical
  26. Graphs
  27. Deblurring
  28. Face Morphing Attack Detection
  29. Trajectory/Motion Prediction
  30. Attacks
  31. Study on data memorization
  32. Out-of-Distribution Detection
  33. Image-to-Text Generation
  34. Quantization
  35. Image/Video anomaly detection
  36. Video-to-Speech
  37. Pose estimation
  38. Graphic layout generation
  39. Image watermarking
  40. Video Editing
  41. Information retrieval from video
  42. Object detection

Content

Unconditional Generation

  1. Deep unsupervised learning using non-equilibrium thermodynamics
  2. Denoising diffusion probabilistic models
  3. Improved techniques for training score-based generative models
  4. Adversarial score matching and improved sampling for image generation
  5. Maximum likelihood training of score-based diffusion models
  6. D2C: Diffusion-Decoding Models for Few-Shot Conditional Generation
  7. Diffusion Normalizing Flow
  8. Diffusion Schrodinger bridge with applications to score-based generative modeling
  9. Structured denoising diffusion models in discrete state-spaces
  10. Score-based generative modeling in latent space
  11. Improved denoising diffusion probabilistic models
  12. Denoising Diffusion Implicit Models
  13. Non-Gaussian denoising diffusion models
  14. Bilateral denoising diffusion models
  15. Unleashing Transformers: Parallel Token Prediction with Discrete Absorbing Diffusion for Fast High-Resolution Image Generation from Vector-Quantized Codes
  16. Noise estimation for generative diffusion models
  17. Gotta go fast when generating data with score-based models
  18. Learning to efficiently sample from diffusion probabilistic models
  19. Deep generative learning via Schrodinger bridge
  20. VAEs meet Diffusion Models: Efficient and High-Fidelity Generation
  21. Variational diffusion models
  22. Score-based generative modeling with critically-damped Langevin diffusion
  23. Tackling the generative learning trilemma with Denoising Diffusion GANs
  24. Heavy-tailed denoising score matching
  25. Analytic-DPM: an Analytic Estimate of the Optimal Reverse Variance in Diffusion Probabilistic Models
  26. Learning Fast Samplers for Diffusion Models by Differentiating Through Sample Quality
  27. Truncated Diffusion Probabilistic Models
  28. Subspace Diffusion Generative Models
  29. Maximum Likelihood Training of Implicit Nonlinear Diffusion Models
  30. On Analyzing Generative and Denoising Capabilities of Diffusion-based Deep Generative Models
  31. Diffusion-GAN: Training GANs with Diffusion
  32. Accelerating Score-based Generative Models for High-Resolution Image Synthesis
  33. Soft Diffusion: Score Matching for General Corruptions
  34. Post-Training Quantization on Diffusion Models
  35. Lookahead Diffusion Probabilistic Models for Refining Mean Estimation
  36. Wavelet Diffusion Models are fast and scalable Image Generators
  37. All are Worth Words: A ViT Backbone for Diffusion Models
  38. Diffusion Probabilistic Model Made Slim
  39. Masked Diffusion Transformer is a Strong Image Synthesizer
  40. DiffFit: Unlocking Transferability of Large Diffusion Models via Simple Parameter-efficient Fine-Tuning
  41. simple diffusion: End-to-end diffusion for high resolution images
  42. Refining Generative Process with Discriminator Guidance in Score-based Diffusion Models

Conditional Generation

  1. Diffusion models beat gans on image synthesis
  2. Classifier-Free Diffusion Guidance
  3. On Fast Sampling of Diffusion Probabilistic Models
  4. DiffuseVAE: Efficient, Controllable and High-Fidelity Generation from Low-Dimensional Latents
  5. Pseudo Numerical Methods for Diffusion Models on Manifolds
  6. Cascaded Diffusion Models for High Fidelity Image Generation
  7. High Fidelity Visualization of What Your Self-Supervised Representation Knows About
  8. Itô-Taylor Sampling Scheme for Denoising Diffusion Probabilistic Models using Ideal Derivatives
  9. {Dynamic Dual-Output Diffusion Models
  10. Generating High Fidelity Data from Low-density Regions using Diffusion Models
  11. Perception Prioritized Training of Diffusion Models
  12. Elucidating the Design Space of Diffusion-Based Generative Models
  13. Progressive distillation for fast sampling of diffusion models
  14. Denoising Likelihood Score Matching for Conditional Score-based Data Generation
  15. On Conditioning the Input Noise for Controlled Image Generation with Diffusion Models
  16. A Continuous Time Framework for Discrete Denoising Models
  17. DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps
  18. Compositional Visual Generation with Composable Diffusion Models
  19. TryOnDiffusion: A Tale of Two UNets
  20. High-Fidelity Guided Image Synthesis with Latent Diffusion Models
  21. Unite and Conquer: Plug & Play Multi-Modal Synthesis using Diffusion Models
  22. Towards Practical Plug-and-Play Diffusion Models
  23. Inversion-based Style Transfer with Diffusion Models
  24. Conditional Text Image Generation with Diffusion Models
  25. Generative Diffusion Prior for Unified Image Restoration and Enhancement
  26. DCFace: Synthetic Face Generation With Dual Condition Diffusion Model
  27. Controllable Light Diffusion for Portraits
  28. LayoutDiffusion: Controllable Diffusion Model for Layout-to-image Generation
  29. Self-Guided Diffusion Models
  30. AdvDiffuser: Natural Adversarial Example Synthesis with Diffusion Models
  31. Pluralistic Aging Diffusion Autoencoder
  32. Improving Sample Quality of Diffusion Models Using Self-Attention Guidance
  33. Generative Novel View Synthesis with 3D-Aware Diffusion Models
  34. Long-Term Photometric Consistent Novel View Synthesis with Diffusion Models
  35. DDFM: Denoising Diffusion Model for Multi-Modality Image Fusion
  36. Steered Diffusion: A Generalized Framework for Plug-and-Play Conditional Image Synthesis
  37. Scalable Diffusion Models with Transformers
  38. HumanSD: A Native Skeleton-Guided Diffusion Model for Human Image Generation
  39. Controllable Person Image Synthesis with Pose-Constrained Latent Diffusion
  40. DiffDreamer: Towards Consistent Unsupervised Single-view Scene Extrapolation with Conditional Diffusion Models
  41. TF-ICON: Diffusion-Based Training-Free Cross-Domain Image Composition
  42. DISCRETE CONTRASTIVE DIFFUSION FOR CROSSMODAL MUSIC AND IMAGE GENERATION

Text-to-Image generation

  1. Vector quantized diffusion model for text-to-image synthesis
  2. Hierarchical text-conditional image generation with CLIP latents
  3. Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding
  4. Fast Sampling of Diffusion Models with Exponential Integrator
  5. DiVAE: Photorealistic Images Synthesis with Denoising Diffusion Decoder
  6. Text-Guided Synthesis of Artistic Images with Retrieval-Augmented Diffusion Models
  7. Text2Human: Text-Driven Controllable Human Image Generation
  8. DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation
  9. SpaText: Spatio-Textual Representation for Controllable Image Generation
  10. MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation
  11. Person Image Synthesis via Denoising Diffusion Model
  12. Uncovering the Disentanglement Capability in Text-to-Image Diffusion Models
  13. Multi-Concept Customization of Text-to-Image Diffusion
  14. ERNIE-ViLG 2.0: Improving Text-to-Image Diffusion Model with Knowledge-Enhanced Mixture-of-Denoising-Experts
  15. Shifted Diffusion for Text-to-image Generation
  16. Specialist Diffusion: Plug-and-Play Sample-Efficient Fine-Tuning of Text-to-Image Diffusion Models To Learn Any Unseen Style
  17. Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Models
  18. Zero-shot spatial layout conditioning for text-to-image diffusion models
  19. Text2Tex: Text-driven Texture Synthesis via Diffusion Models
  20. Ablating Concepts in Text-to-Image Diffusion Models
  21. Editing Implicit Assumptions in Text-to-Image Diffusion Models
  22. Harnessing the Spatial-Temporal Attention of Diffusion Models for High-Fidelity Text-to-Image Synthesis
  23. Localizing Object-Level Shape Variations with Text-to-Image Diffusion Models
  24. MagicFusion: Boosting Text-to-Image Generation Performance by Fusing Diffusion Models
  25. BoxDiff: Text-to-Image Synthesis with Training-Free Box-Constrained Diffusion
  26. Diffusion in Style
  27. DiffCloth: Diffusion Based Garment Synthesis and Manipulation via Structural Cross-modal Semantic Alignment
  28. LAW-Diffusion: Complex Scene Generation by Diffusion with Layouts
  29. Discriminative Class Tokens for Text-to-Image Diffusion Models
  30. Cones: Concept Neurons in Diffusion Models for Customized Generation
  31. MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation

Super-Resolution

  1. Image super-resolution via iterative refinement
  2. Score-based Generative Neural Networks for Large-Scale Optimal Transport
  3. Implicit Diffusion Models for Continuous Super-Resolution
  4. HSR-Diff: Hyperspectral Image Super-Resolution via Conditional Diffusion Models

Image Editing

  1. SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations
  2. Blended Latent Diffusion
  3. SINE: SINgle Image Editing with Text-to-Image Diffusion Models
  4. Imagic: Text-Based Real Image Editing with Diffusion Models
  5. Collaborative Diffusion for Multi-Modal Face Generation and Editing
  6. Null-text Inversion for Editing Real Images using Guided Diffusion Models
  7. DiffusionRig: Learning Personalized Priors for Facial Appearance Editing
  8. RenderDiffusion: Image Diffusion for 3D Reconstruction, Inpainting and Generation
  9. Paint by Example: Exemplar-based Image Editing with Diffusion Models
  10. Effective Real Image Editing with Accelerated Iterative Diffusion Inversion
  11. SVDiff: Compact Parameter Space for Diffusion Fine-Tuning
  12. Multimodal Garment Designer: Human-Centric Latent Diffusion Models for Fashion Image Editing
  13. Boundary-Aware Divide and Conquer: A Diffusion-Based Solution for Unsupervised Shadow Removal
  14. Not All Steps are Created Equal: Selective Diffusion Distillation for Image Manipulation
  15. Prompt Tuning Inversion for Text-driven Image Editing Using Diffusion Models
  16. DiFaReli: Diffusion Face Relighting

Region Image Editing

  1. Blended diffusion for text-driven editing of natural images

Inpainting

  1. GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models
  2. RePaint: Inpainting using Denoising Diffusion Probabilistic Models
  3. [RGBD2: Generative Scene Synthesis via Incremental View Inpainting using RGBD Diffusion Models] (https://openaccess.thecvf.com/content/CVPR2023/papers/Lei_RGBD2_Generative_Scene_Synthesis_via_Incremental_View_Inpainting_Using_RGBD_CVPR_2023_paper.pdf) 4.SmartBrush: Text and Shape Guided Object Inpainting With Diffusion Model
  4. DINAR: Diffusion Inpainting of Neural Textures for One-Shot Human Avatars
  5. Towards Coherent Image Inpainting Using Denoising Diffusion Implicit Models

Image-to-Image Translation

  1. Palette: Image-to-Image Diffusion Models
  2. UNIT-DDPM: UNpaired Image Translation with Denoising Diffusion Probabilistic Models
  3. EGSDE: Unpaired Image-to-Image Translation via Energy-Guided Stochastic Differential Equations
  4. Pretraining is All You Need for Image-to-Image Translation
  5. VQBB: Image-to-image Translation with Vector Quantized Brownian Bridge
  6. The Swiss Army Knife for Image-to-Image Translation: Multi-Task Diffusion Models
  7. Unifying Diffusion Models' Latent Space, with Applications to CycleDiffusion and Guidance
  8. BBDM: Image-to-Image Translation with Brownian Bridge Diffusion Models
  9. Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation
  10. Zero-Shot Contrastive Loss for Text-Guided Diffusion Image Style Transfer
  11. StyleDiffusion: Controllable Disentangled Style Transfer via Diffusion Models
  12. Diffusion-based Image Translation with Label Guidance for Domain Adaptive Semantic Segmentation
  13. Dual Diffusion Implicit Bridges for Image-to-Image Translation

Image Segmentation

  1. Label-Efficient Semantic Segmentation with Diffusion Models
  2. SegDiff: Image Segmentation with Diffusion Probabilistic Models
  3. Multi-Class Segmentation from Aerial Views using Recursive Noise Diffusion
  4. Ambiguous Medical Image Segmentation using Diffusion Models
  5. LD-ZNet: A Latent Diffusion Approach for Text-Based Image Segmentation
  6. Open-vocabulary Object Segmentation with Diffusion Models

Multi-Task

  1. Generative modeling by estimating gradients of the data distribution
  2. Score-Based Generative Modeling through Stochastic Differential Equations
  3. ImageBART: Bidirectional Context with Multinomial Diffusion for Autoregressive Image Synthesis
  4. Learning Energy-Based Models by Diffusion Recovery Likelihood
  5. Conditional image generation with score-based diffusion models
  6. More control for free! Image synthesis with semantic diffusion guidance
  7. ILVR: Conditioning Method for Denoising Diffusion Probabilistic Models
  8. Global Context with Discrete Diffusion in Vector Quantised Modelling for Image Generation
  9. High-Resolution Image Synthesis with Latent Diffusion Models
  10. Diffusion Autoencoders: Toward a Meaningful and Decodable Representation
  11. Come-Closer-Diffuse-Faster: Accelerating Conditional Diffusion Models for Inverse Problems through Stochastic Contraction
  12. DiffusionCLIP: Text-Guided Diffusion Models for Robust Image Manipulation
  13. Understanding DDPM Latent Codes Through Optimal Transport
  14. Conditional Simulation Using Diffusion Schrödinger Bridges
  15. Retrieval-Augmented Diffusion Models
  16. Accelerating Diffusion Models via Early Stop of the Diffusion Process
  17. Diffusion Models as Plug-and-Play Priors
  18. Non-Uniform Diffusion Models
  19. Diffusion Probabilistic Model Made Slim
  20. Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models
  21. On Distillation of Guided Diffusion Model
  22. DiffCollage: Parallel Generation of Large Content With Diffusion Models
  23. EGC: Image Generation and Classification via a Diffusion Energy-Based Model
  24. Diffusion Models as Masked Autoencoders
  25. Versatile Diffusion: Text, Images and Variations All in One Diffusion Model
  26. A Latent Space of Stochastic Diffusion Models for Zero-Shot Image Editing and Guidance
  27. Adding Conditional Control to Text-to-Image Diffusion Models
  28. FreeDoM: Training-Free Energy-Guided Conditional Diffusion Model
  29. SinDDM: A Single Image Denoising Diffusion Model

Medical Image-to-Image Translation

  1. Unsupervised Medical Image Translation with Adversarial Diffusion Models
  2. Unsupervised Denoising of Retinal OCT with Diffusion Probabilistic Model
  3. Conversion Between CT and MRI Images Using Diffusion and Score-Matching Models

Medical Image Generation

  1. Solving inverse problems in medical imaging with score-based generative models
  2. Score-based diffusion models for accelerated MRI
  3. Diffusion Models For Medical Image Analysis: A Comprehensive Survey
  4. Low-Dose CT Using Denoising Diffusion Probabilistic Model for 20× Speedup
  5. Solving 3D Inverse Problems using Pre-trained 2D Diffusion Models
  6. DOLCE: A Model-Based Probabilistic Diffusion Framework for Limited-Angle CT Reconstruction

Medical Image Segmentation

  1. Diffusion Models for Implicit Image Segmentation Ensembles
  2. Accelerating Diffusion Models via Pre-segmentation Diffusion Sampling for Medical Image Segmentation
  3. Stochastic Segmentation with Conditional Categorical Diffusion Models

Medical Image Anomaly Detection

  1. Diffusion Models for Medical Anomaly Detection
  2. Fast Unsupervised Brain Anomaly Detection and Segmentation with Diffusion Models
  3. AnoDDPM: Anomaly Detection With Denoising Diffusion Probabilistic Models Using Simplex Noise
  4. What is Healthy? Generative Counterfactual Diffusion for Lesion Localization

Video Generation

  1. Video Diffusion Models
  2. Diffusion Probabilistic Modeling for Video Generation
  3. Flexible Diffusion Modeling of Long Videos
  4. Diffusion Models for Video Prediction and Infilling
  5. Dreamix: Video Diffusion Models are General Video Editors
  6. Conditional Image-to-Video Generation with Latent Flow Diffusion Models
  7. DiffTalk: Crafting Diffusion Models for Generalized Audio-Driven Portraits Animation
  8. MM-Diffusion: Learning Multi-Modal Diffusion Models for Joint Audio and Video Generation
  9. VideoFusion: Decomposed Diffusion Models for High-Quality Video Generation
  10. Video Probabilistic Diffusion Models in Projected Latent Space
  11. Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models
  12. Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation
  13. Preserve Your Own Correlation: A Noise Prior for Video Diffusion Models
  14. Talking Head Generation with Probabilistic Audio-to-Visual Diffusion Priors
  15. DreamPose: Fashion Video Synthesis with Stable Diffusion
  16. The Power of Sound (TPoS): Audio Reactive Video Generation with Stable Diffusion
  17. Structure and Content-Guided Video Synthesis with Diffusion Models
  18. Text2Video-Zero: Text-to-Image Diffusion Models are Zero-Shot Video Generators
  19. SinFusion: Training Diffusion Models on a Single Image or Video

Few-Shot Image Generation

  1. Few-Shot Diffusion Models

Counterfactual Explanations and Estimations

  1. Diffusion Models for Counterfactual Explanations
  2. Diffusion Causal Models for Counterfactual Estimation

Image Restoration

  1. Restoring Vision in Adverse Weather Conditions with Patch-Based Denoising Diffusion Models
  2. Denoising Diffusion Restoration Models
  3. Diffusion in the Dark: A Diffusion Model for Low-Light Text Recognition
  4. High-resolution image reconstruction with latent diffusion models from human brain activity
  5. Seeing Beyond the Brain: Conditional Diffusion Model with Sparse Masked Modeling for Vision Decoding
  6. Diff-Retinex: Rethinking Low-light Image Enhancement with A Generative Diffusion Model
  7. Towards Authentic Face Restoration with Iterative Diffusion Models and Beyond
  8. DDS2M: Self-Supervised Denoising Diffusion Spatio-Spectral Model for Hyperspectral Image Restoration
  9. DiffIR: Efficient Diffusion Model for Image Restoration
  10. Innovating Real Fisheye Image Correction with Dual Diffusion Architecture

Image Registration

  1. DiffuseMorph: Unsupervised Deformable Image Registration Along Continuous Trajectory Using Diffusion Models

Adversarial Purification

  1. Diffusion Models for Adversarial Purification
  2. Robust Evaluation of Diffusion-Based Adversarial Purification

Semantic Image Generation

  1. Semantic Image Synthesis via Diffusion Models
  2. DiffuMask: Synthesizing Images with Pixel-level Annotations for Semantic Segmentation Using Diffusion Models
  3. DDP: Diffusion Model for Dense Visual Prediction

3D Generation

  1. 3D shape generation and completion through point-voxel diffusion
  2. RODIN: A Generative Model for Sculpting 3D Digital Avatars Using Diffusion
  3. Avatars Grow Legs: Generating Smooth Human Motion from Sparse Tracking Inputs with Diffusion Model
  4. NeuralField-LDM: Scene Generation with Hierarchical Latent Diffusion Models
  5. Diffusion-SDF: Text-to-Shape via Voxelized Diffusion
  6. Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation
  7. DATID-3D: Diversity-Preserved Domain Adaptation Using Text-to-Image Diffusion for 3D Generative Model
  8. HOLODIFFUSION: Training a 3D Diffusion Model using 2D Images
  9. Dream3D: Zero-Shot Text-to-3D Synthesis Using 3D Shape Prior and Text-to-Image Diffusion Models
  10. Consistent View Synthesis with Pose-Guided Diffusion Models
  11. Texture Generation on 3D Meshes with Point-UV Diffusion
  12. DiffFacto: Controllable Part-Based 3D Point Cloud Generation with Cross Diffusion
  13. Chupa: Carving 3D Clothed Humans from Skinned Shape Priors using 2D Diffusion Probabilistic Models
  14. Guided Motion Diffusion for Controllable Human Motion Synthesis
  15. Unaligned 2D to 3D Translation with Conditional Vector-Quantized Code Diffusion using Transformers
  16. Make-It-3D: High-fidelity 3D Creation from A Single Image with Diffusion Prior
  17. TexFusion: Synthesizing 3D Textures with Text-Guided Image Diffusion Models
  18. Viewset Diffusion: (0-)Image-Conditioned 3D Generative Models from 2D Data
  19. 3D-aware Image Generation using 2D Diffusion Models
  20. Diffusion-Guided Reconstruction of Everyday Hand-Object Interaction Clips
  21. Single-Stage Diffusion NeRF: A Unified Approach to 3D Generation and Reconstruction
  22. Diffusion-SDF: Conditional Generative Modeling of Signed Distance Functions
  23. SALAD: Part-Level Latent Diffusion for 3D Shape Generation and Manipulation
  24. DG3D: Generating High Quality 3D Textured Shapes by Learning to Discriminate Multi-Modal Diffusion-Renderings
  25. Relightify: Relightable 3D Faces from a Single Image via Diffusion Models
  26. Distribution-Aligned Diffusion for Human Mesh Recovery
  27. Diffuse3D: Wide-Angle 3D Photography via Bilateral Diffusion
  28. PODIA-3D: Domain Adaptation of 3D Generative Model Across Large Domain Gap Using Pose-Preserved Text-to-Image Diffusion
  29. HyperDiffusion: Generating Implicit Neural Fields with Weight-Space Diffusion
  30. Improving 3D Imaging with Pre-Trained Perpendicular 2D Diffusion Models

Classification

  1. Score-based generative classifiers
  2. Diffusion-based Data Augmentation for Skin Disease Classification: Impact Across Original Medical Datasets to Fully Synthetic Images
  3. IDiff-Face: Synthetic-based Face Recognition through Fizzy Identity-Conditioned Diffusion Models
  4. DIRE for Diffusion-Generated Image Detection
  5. Denoising Diffusion Autoencoders are Unified Self-supervised Learners
  6. Your Diffusion Model is Secretly a Zero-Shot Classifier

Point Cloud Generation

  1. Diffusion Probabilistic Models for 3D Point Cloud Generation
  2. Sketch and Text Guided Diffusion Model for Colored Point Cloud Generation
  3. GECCO: Geometrically-Conditioned Point Diffusion Models

Theoretical

  1. A variational perspective on diffusion-based generative models and score matching
  2. Sampling is as easy as learning the score: theory for diffusion models with minimal data assumptions
  3. Erasing Concepts from Diffusion Models
  4. A Complete Recipe for Diffusion Generative Models
  5. Efficient Diffusion Training via Min-SNR Weighting Strategy
  6. Phasic Content Fusing Diffusion Model with Directional Distribution Consistency for Few-Shot Model Adaption
  7. AutoDiffusion: Training-Free Optimization of Time Steps and Architectures for Automated Diffusion Model Acceleration
  8. End-to-End Diffusion Latent Optimization Improves Classifier Guidance
  9. Score-Based Diffusion Models as Principled Priors for Inverse Imaging
  10. Diffusion Model as Representation Learner
  11. DPM-OT: A New Diffusion Probabilistic Model Based on Optimal Transport
  12. Unleashing Text-to-Image Diffusion Models for Visual Perception

Graphs

  1. Generative Diffusion Models on Graphs: Methods and Applications

Deblurring

  1. Image Deblurring with Domain Generalizable Diffusion Models
  2. Multiscale Structure Guided Diffusion for Image Deblurring

Face Morphing Attack Detection

  1. Face Morphing Attack Detection with Denoising Diffusion Probabilistic Models

Trajectory/Motion Prediction

  1. Leapfrog Diffusion Model for Stochastic Trajectory Prediction
  2. Fg-T2M: Fine-Grained Text-Driven Human Motion Generation via Diffusion Model
  3. PhysDiff: Physics-Guided Human Motion Diffusion Model
  4. Hierarchical Generation of Human-Object Interactions with Diffusion Probabilistic Models
  5. Diffusion-Based 3D Human Pose Estimation with Multi-Hypothesis Aggregation
  6. ReMoDiffuse: Retrieval-Augmented Motion Diffusion Model
  7. InterDiff: Generating 3D Human-Object Interactions with Physics-Informed Diffusion
  8. BeLFusion: Latent Diffusion for Behavior-Driven Human Motion Prediction
  9. Social Diffusion: Long-term Multiple Human Motion Anticipation

Attacks

  1. How to Backdoor Diffusion Models?
  2. TrojDiff: Trojan Attacks on Diffusion Models with Diverse Targets

Study on data memorization

1.Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Models

Out-of-Distribution Detection

  1. DIFFGUARD: Semantic Mismatch-Guided Out-of-Distribution Detection Using Pre-Trained Diffusion Models
  2. Deep Feature Deblurring Diffusion for Detecting Out-of-Distribution Objects
  3. Unsupervised Out-of-Distribution Detection with Diffusion Inpainting

Image-to-Text Generation

  1. DiffTAD: Temporal Action Detection with Proposal Denoising Diffusion

Quantization

  1. Q-Diffusion: Quantizing Diffusion Models

Image/Video anomaly detection

  1. Feature Prediction Diffusion Model for Video Anomaly Detection
  2. Unsupervised Surface Anomaly Detection with Diffusion Probabilistic Model
  3. Multimodal Motion Conditioned Diffusion Model for Skeleton-based Video Anomaly Detection

Video-to-Speech

  1. DiffV2S: Diffusion-Based Video-to-Speech Synthesis with Vision-Guided Speaker Embedding

Pose estimation

  1. DiffPose: Multi-hypothesis Human Pose Estimation using Diffusion Models
  2. PoseDiffusion: Solving Pose Estimation via Diffusion-aided Bundle Adjustment
  3. DiffPose: SpatioTemporal Diffusion Model for Video-Based Human Pose Estimation

Graphic layout generation

  1. LayoutDiffusion: Improving Graphic Layout Generation by Discrete Diffusion Probabilistic Models
  2. DLT: Conditioned layout generation with Joint Discrete-Continuous Diffusion Layout Transformer

Image watermarking

  1. The Stable Signature: Rooting Watermarks in Latent Diffusion Models

Video Editing

  1. Diffusion Video Autoencoders: Toward Temporally Consistent Face Video Editing via Disentangled Video Encoding
  2. Pix2Video: Video Editing using Image Diffusion
  3. StableVideo: Text-driven Consistency-aware Diffusion Video Editing

Information retrieval from video

  1. DiffusionRet: Generative Text-Video Retrieval with Diffusion Model
  2. Diffusion Action Segmentation

Object detection

  1. DiffusionDet: Diffusion Model for Object Detection