Denoising Diffusion Probabilistic Models
PulseAugur coverage of Denoising Diffusion Probabilistic Models — every cluster mentioning Denoising Diffusion Probabilistic Models across labs, papers, and developer communities, ranked by signal.
5 day(s) with sentiment data
-
New 3D Diffusion Model Enhances Brain MRI Lesion Inpainting
Researchers have developed a novel 3D diffusion model for longitudinal lesion inpainting in brain MRI scans. This framework, based on Denoising Diffusion Probabilistic Models (DDPM), uses multi-channel conditioning to i…
-
New HDDPM model enhances low-count PET image recovery
Researchers have developed a new method called HDDPM (Heteroscedastic Denoising Diffusion Probabilistic Model) to improve the recovery of low-count Positron Emission Tomography (PET) images. Unlike standard diffusion mo…
-
Paper Unifies Diffusion Models and Flow Matching via Wasserstein Geometry
This paper explores the underlying geometry of diffusion models and flow matching, revealing that both are governed by the quadratic Wasserstein distance on the space of probability measures. The research posits that di…
-
Diffusion models generate synthetic TEM images for semiconductor metrology
Researchers have developed a Denoising Diffusion Probabilistic Model (DDPM) to generate high-fidelity synthetic Transmission Electron Microscopy (TEM) images for semiconductor metrology. This approach addresses the scar…
-
New cyclic denoising attack reveals "ultrastable memories" in diffusion models
Researchers have developed a new technique called cyclic denoising to probe image diffusion models for memorized training data. This method involves repeatedly applying forward and reverse diffusion processes at control…
-
New AI models offer faster, more efficient medical image translation
Researchers have developed new methods for medical image translation that are faster and more efficient than existing diffusion models. One study introduces a lightweight U-Net that outperforms a state-of-the-art Denois…
-
Diffusion-SAC enhances UAV network control with AI
Researchers have developed a new approach called Diffusion-SAC that combines offline reinforcement learning with denoising diffusion probabilistic models to optimize control in unmanned aerial vehicle (UAV) networks for…
-
Synthetic image models tested for data scarcity and privacy
A new study published on arXiv examines the effectiveness of synthetic image generation models like VAE, GAN, and DDPM when faced with limited data and privacy concerns. Researchers developed a framework to evaluate fid…
-
AI model removes clouds from flood satellite imagery
Researchers have developed a new cloud-removal framework for flood imagery using Denoising Diffusion Probabilistic Models and a Masked Diffusion Transformer architecture. This method aims to improve flood inundation map…
-
Diffusion model theory reveals DDIM's hallucination weakness
A new theoretical analysis examines hallucination phenomena in diffusion models, specifically comparing the Denoising Diffusion Probabilistic Model (DDPM) and the Denoising Diffusion Implicit Model (DDIM). The study pro…
-
Diffusion models struggle with discrete data; new methods improve quality
Researchers have identified a key issue with Gaussian diffusion models when applied to discrete data, specifically noting that the DDPM solver struggles with sampling intervals that lead to multimodal distributions. Thi…
-
New Physics-Informed Diffusion Model Enhances Chaotic System Reconstruction
Researchers have developed PIDM-DP, a novel Physics-Informed Diffusion Model that integrates a Dormand-Prince ODE integrator into a Denoising Diffusion Probabilistic Model. This approach constrains generated trajectorie…
-
AI generates fMRI time series to improve depression diagnosis
Researchers have developed fMRI-Diffusion, a novel framework that generates synthetic fMRI time series data to aid in the diagnosis of Major Depressive Disorder (MDD). Unlike previous methods that synthesize functional …
-
New Gaussian Mixture Model improves DDIM sampling quality
Researchers have developed a new method to improve the sampling process in Denoising Diffusion Implicit Models (DDIM). Their approach utilizes a Gaussian Mixture Model (GMM) as the reverse transition operator, which mat…
-
New research links Föllmer processes to DDPMs, improving sampling efficiency
Researchers have explored the connection between Föllmer processes and denoising diffusion probabilistic models (DDPMs), finding that discretizing Föllmer processes can yield optimal hyper-parameter settings for DDPM sa…
-
ExpoCM framework reconstructs HDR images faster
Researchers have developed ExpoCM, a new framework for reconstructing high dynamic range (HDR) images from single low dynamic range inputs. This method addresses the challenges of detail loss in over-exposed and noise i…