Saved in:
Bibliographic Details
Main Authors: Falaleev, Nikolay, Orlov, Nikolai
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2504.16951
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916924381724672
author Falaleev, Nikolay
Orlov, Nikolai
author_facet Falaleev, Nikolay
Orlov, Nikolai
contents This paper presents a novel approach for denoising Electron Backscatter Diffraction (EBSD) patterns using diffusion models. We propose a two-stage training process with a UNet-based architecture, incorporating an auxiliary regression head to predict the quality of the experimental pattern and assess the progress of the denoising process. The model uses an adaptive denoising strategy, which integrates quality prediction and feedback-driven iterative denoising process control. This adaptive feedback loop allows the model to adjust its schedule, providing fine control over the denoising process. Furthermore, our model can identify samples where no meaningful signal is present, thereby reducing the risk of hallucinations. We demonstrate the DIFFRACT - the successful application of diffusion models to EBSD pattern denoising using a custom-collected dataset of EBSD patterns, their corresponding Master Patterns, and quality values.
format Preprint
id arxiv_https___arxiv_org_abs_2504_16951
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DIFFRACT: Diffusion-based Restoration via Adaptive Control and Thresholding for Diffraction Imaging
Falaleev, Nikolay
Orlov, Nikolai
Image and Video Processing
This paper presents a novel approach for denoising Electron Backscatter Diffraction (EBSD) patterns using diffusion models. We propose a two-stage training process with a UNet-based architecture, incorporating an auxiliary regression head to predict the quality of the experimental pattern and assess the progress of the denoising process. The model uses an adaptive denoising strategy, which integrates quality prediction and feedback-driven iterative denoising process control. This adaptive feedback loop allows the model to adjust its schedule, providing fine control over the denoising process. Furthermore, our model can identify samples where no meaningful signal is present, thereby reducing the risk of hallucinations. We demonstrate the DIFFRACT - the successful application of diffusion models to EBSD pattern denoising using a custom-collected dataset of EBSD patterns, their corresponding Master Patterns, and quality values.
title DIFFRACT: Diffusion-based Restoration via Adaptive Control and Thresholding for Diffraction Imaging
topic Image and Video Processing
url https://arxiv.org/abs/2504.16951