Phase-fraction guided denoising diffusion model for augmenting multiphase steel microstructure segmentation via micrograph image-mask pair synthesis

TL;DR

This paper presents PF-DiffSeg, a diffusion model that synthesizes microstructure images and masks conditioned on phase fractions, significantly enhancing segmentation accuracy for complex steel microstructures.

Contribution

Introduction of a phase-fraction guided diffusion framework that jointly generates microstructure images and masks, improving data diversity and segmentation performance in metallography.

Findings

Improves segmentation accuracy, especially for minority classes.

Outperforms GAN and two-stage diffusion baselines.

Reduces inference time compared to traditional methods.

Abstract

The effectiveness of machine learning in metallographic microstructure segmentation is often constrained by the lack of human-annotated phase masks, particularly for rare or compositionally complex morphologies within the metal alloy. We introduce PF-DiffSeg, a phase-fraction controlled, one-stage denoising diffusion framework that jointly synthesizes microstructure images and their corresponding segmentation masks in a single generative trajectory to further improve segmentation accuracy. By conditioning on global phase-fraction vectors, augmented to represent real data distribution and emphasize minority classes, our model generates compositionally valid and structurally coherent microstructure image and mask samples that improve both data diversity and training efficiency. Evaluated on the MetalDAM benchmark for additively manufactured multiphase steel, our synthetic augmentation method yields notable improvements in segmentation accuracy compared to standard augmentation strategies especially in minority classes and further outperforms a two-stage mask-guided diffusion and generative adversarial network (GAN) baselines, while also reducing inference time compared to conventional approach. The method integrates generation and conditioning into a unified framework, offering a scalable solution for data augmentation in metallographic applications.