Generating Synthetic Spectral Data using Conditional DDPM
Fabian Kubiczek, Stefan Patzke, Jörg Thiem · 2025
This study investigates the efficiency and effectiveness of Denoising Diffusion Probabilistic Models (DDPM) for generating synthetic spectral data.A modified DDPM was implemented and evaluated in comparison to a previously established model.Both models were trained with and without Classifier-Free Guidance (CFG).In addition, training duration and sample generation are compared.The results demonstrate that the synthetic spectral data exhibits a high degree of alignment with the training data, with only minor deviations.Furthermore, the influence of CFG on the generation process is evident.The findings indicate that the modified DDPM performs better on the given data. MethodsIn this section, we present the utilized dataset, provide a detailed description of the design and implementation of the U-Net architecture, define the diffusion process and outline the evaluation methods employed.Spatial information is not considered in this study.This allows the generated spectra to be used for applications with a per-pixel basis, where individual data points lack spatial context.