Diffusion Model

Diffusion models are generative models that create data by reversing a noise-diffusion process, aiming to generate high-quality samples from complex distributions. Current research focuses on improving efficiency through techniques like stochastic Runge-Kutta methods and dynamic model architectures (e.g., Dynamic Diffusion Transformer), as well as enhancing controllability and safety via methods such as classifier-free guidance and reinforcement learning from human feedback. These advancements are significantly impacting various fields, including medical imaging, robotics, and artistic creation, by enabling novel applications in image generation, inverse problem solving, and multi-modal data synthesis.

2251papers

Papers - Page 31

November 16, 2024

Diffusion-based Layer-wise Semantic Reconstruction for Unsupervised Out-of-Distribution Detection
Unsupervised Out of Distribution Distribution Detection Data Reconstruction Unsupervised Setting Diffusion Model
MaskMedPaint: Masked Medical Image Inpainting with Diffusion Models for Mitigation of Spurious Correlations
Faulty Negative Mitigation Diffusion Probabilistic Model Text to Image Diffusion Model Medical Image Diffusion Model Medical Image Enhancement Spurious Correlation Spurious Feature

November 15, 2024

Probabilistic Prior Driven Attention Mechanism Based on Diffusion Model for Imaging Through Atmospheric Turbulence
Denoising Diffusion Probabilistic Model Atmospheric Turbulence Imaging Technique Image Restoration Turbulent Image Diffusion Prior Diffusion Model
DR-BFR: Degradation Representation with Diffusion Models for Blind Face Restoration
Blind Face Restoration Restoration Quality Blind Inverse Problem Diffusion Model Degradation Representation Latent Diffusion Model Diffusion Restoration
The Unreasonable Effectiveness of Guidance for Diffusion Models
Image Fidelity Diffusion Model Auxiliary Model Guidance Law Human Guidance Temporal Dependency
ColorEdit: Training-free Image-Guided Color editing with diffusion model
Image Synthesis Color Correction Cross Attention Block Image Editing Diffusion Model
Adaptive Non-Uniform Timestep Sampling for Diffusion Model Training
Diffusion Model Architecture Step Sampling Sampling Technique Stochastic Gradient Diffusion Model

November 14, 2024

Golden Noise for Diffusion Models: A Learning Framework
Gaussian Noise Background Noise Diffusion Model Diffusion Sampling Text to Image Diffusion Model Learning Framework
EEG-Based Speech Decoding: A Novel Approach Using Multi-Kernel Ensemble Diffusion Models
Diffusion Model Kernel Learning Conditional Autoencoder Novel Approach Brain Signal Neural Signal Ensemble Method

November 13, 2024

Inconsistencies In Consistency Models: Better ODE Solving Does Not Imply Better Samples
Consistency Model Diffusion Model Sample Quality Hard to Easy Inconsistency
Offline Adaptation of Quadruped Locomotion using Diffusion Models
Diffusion Based Quadruped Locomotion Human Like Locomotion Behavior Quadrupedal Locomotion Diffusion Model Goal Conditioned Locomotion Strategy
Physics Informed Distillation for Diffusion Models
Probability Flow ODE Implicit Model Distillation Framework Diffusion Model

November 12, 2024

Scaling Properties of Diffusion Models for Perceptual Tasks
Diffusion Model Scaling Behavior Optical Flow Image to Image Translation Visual Perception Perception Task
Structured Pattern Expansion with Diffusion Models
Stationary Distribution Diffusion Model Complex Pattern Pre Trained Image Diffusion Model
Novel View Synthesis with Pixel-Space Diffusion Models
Generative Model Training Scheme Diffusion Model Novel View Synthesis
Unraveling the Connections between Flow Matching and Diffusion Probabilistic Models in Training-free Conditional Generation
Diffusion Explainer New Connection Probabilistic Model High Quality Generation Conditional Generation Flow Matching Diffusion Model
Tracing the Roots: Leveraging Temporal Dynamics in Diffusion Trajectories for Origin Attribution
Diffusion Explainer SHUSS Root Exploration Term Diffusion Model Pre Trained Diffusion Model Handwritten Trajectory Discriminative Classifier Temporal Dynamic Diffusion Trajectory

Diffusion Model

Papers - Page 31

Diffusion-based Layer-wise Semantic Reconstruction for Unsupervised Out-of-Distribution Detection

MaskMedPaint: Masked Medical Image Inpainting with Diffusion Models for Mitigation of Spurious Correlations

Probabilistic Prior Driven Attention Mechanism Based on Diffusion Model for Imaging Through Atmospheric Turbulence

DR-BFR: Degradation Representation with Diffusion Models for Blind Face Restoration

The Unreasonable Effectiveness of Guidance for Diffusion Models

ColorEdit: Training-free Image-Guided Color editing with diffusion model

Adaptive Non-Uniform Timestep Sampling for Diffusion Model Training

Golden Noise for Diffusion Models: A Learning Framework

EEG-Based Speech Decoding: A Novel Approach Using Multi-Kernel Ensemble Diffusion Models

Inconsistencies In Consistency Models: Better ODE Solving Does Not Imply Better Samples

Offline Adaptation of Quadruped Locomotion using Diffusion Models

Physics Informed Distillation for Diffusion Models

Scaling Properties of Diffusion Models for Perceptual Tasks

Structured Pattern Expansion with Diffusion Models

Novel View Synthesis with Pixel-Space Diffusion Models

Unraveling the Connections between Flow Matching and Diffusion Probabilistic Models in Training-free Conditional Generation

Tracing the Roots: Leveraging Temporal Dynamics in Diffusion Trajectories for Origin Attribution

Score-based generative diffusion with "active" correlated noise sources

Add-it: Training-Free Object Insertion in Images With Pretrained Diffusion Models

OmniEdit: Building Image Editing Generalist Models Through Specialist Supervision