Related papers: Generative diffusion modeling protocols for improv…
Diffusion models show promise for image restoration, but existing methods often struggle with inconsistent fidelity and undesirable artifacts. To address this, we introduce Kernel Density Steering (KDS), a novel inference-time framework…
Acquiring high-quality data for training discriminative models is a crucial yet challenging aspect of building effective predictive systems. In this paper, we present Diffusion Inversion, a simple yet effective method that leverages the…
While learned image compression (LIC) focuses on efficient data transmission, generative image compression (GIC) extends this framework by integrating generative modeling to produce photo-realistic reconstructed images. In this paper, we…
The three scanning electron microscope diffraction based techniques of electron channelling patterns (ECPs), electron channelling contrast imaging (ECCI), and electron back scatter diffraction (EBSD) are reviewed. The dynamical diffraction…
Analysis of distortions of the crystal lattice within individual mineral grains is central to the investigation of microscale processes that control and record tectonic events. These distortions are generally combinations of lattice…
Electron backscatter diffraction is a powerful tool for mapping crystallographic microstructures. However, the primary crux to improving orientation accuracy and applying the technique to challenging materials lies in the correct…
4D-STEM-based orientation and phase mapping has enabled rapid microstructure quantification that can be directly combined with standard TEM- and STEM-based imaging modes. Typically, orientation mapping is coupled with beam precession (i.e.…
Diffusion models are a powerful generative framework, but come with expensive inference. Existing acceleration methods often compromise image quality or fail under complex conditioning when operating in an extremely low-step regime. In this…
High angular resolution electron backscatter diffraction (HR-EBSD) affords an increase in angular resolution, as compared to 'conventional' Hough transform based EBSD, of two orders of magnitude, enabling measurements of relative…
We present significant extensions to diffusion-based sequence generation models, blurring the line with autoregressive language models. We introduce hyperschedules, which assign distinct noise schedules to individual token positions,…
With the rapid development of deep learning, existing generative text steganography methods based on autoregressive models have achieved success. However, these autoregressive steganography approaches have certain limitations. Firstly,…
The study of thin films and 2D materials, including transition metal dichalcogenides such as WSe$_2$ offers opportunities to leverage their properties in advanced sensors, quantum technologies, and device to optimize functional performance.…
The performance of pre-trained masked diffusion models is often constrained by their sampling procedure, which makes decisions irreversible and struggles in low-step generation regimes. We introduce a novel sampling algorithm that works…
Accurate quantification of the energy distribution of backscattered electrons (BSEs) contributing to electron backscatter diffraction (EBSD) patterns remains as an active challenge. This study introduces an energy-resolved EBSD methodology…
In this work, we build upon our previous publication and use diffusion-based generative models for speech enhancement. We present a detailed overview of the diffusion process that is based on a stochastic differential equation and delve…
Magnetic resonance imaging (MRI) is a powerful medical imaging modality, but long acquisition times limit throughput, patient comfort, and clinical accessibility. Diffusion-based generative models serve as strong image priors for reducing…
Diffusion generative models transform noise into data by inverting a process that progressively adds noise to data samples. Inspired by concepts from the renormalization group in physics, which analyzes systems across different scales, we…
Diffusion models are powerful generative models that achieve state-of-the-art performance in image synthesis. However, training them demands substantial amounts of data and computational resources. Continual learning would allow for…
Employing a forward diffusion chain to gradually map the data to a noise distribution, diffusion-based generative models learn how to generate the data by inferring a reverse diffusion chain. However, this approach is slow and costly…
Edge detection is typically viewed as a pixel-level classification problem mainly addressed by discriminative methods. Recently, generative edge detection methods, especially diffusion model based solutions, are initialized in the edge…