SAMamba3D: adapting Segment Anything for generalizable 3D segmentation of multiphase pore-scale images

TL;DR

SAMamba3D introduces a novel, efficient framework that adapts the Segment Anything Model for robust, generalizable 3D segmentation of multiphase pore-scale images, reducing retraining needs.

Contribution

It presents a new method coupling a frozen SAM encoder with volumetric modeling for 3D segmentation, outperforming existing methods across diverse datasets.

Findings

Matches or outperforms current 3D segmentation baselines.

Reduces the need for case-specific retraining.

Preserves physically meaningful descriptors in segmented images.

Abstract

Reliable segmentation of multiphase pore-scale X-ray images of rocks is necessary to quantify fluid saturation, connectivity, and interfacial geometry. However, current 3D segmentation methods are typically dataset-specific, requiring retraining or extensive fine-tuning whenever rock type, fluid pattern, scanner, or acquisition conditions change. Foundation models such as the Segment Anything Model (SAM) provide strong 2D boundary priors, but they are not directly applicable to 3D data. We present SAMamba3D, a parameter-efficient framework that adapts a largely frozen SAM encoder to generalizable 3D pore-scale segmentation by coupling it with Mamba-based volumetric context modeling and progressive cross-scale feature interaction. For sandstone and carbonate datasets, with different fluids, wettability, and scanning conditions, SAMamba3D matches or outperforms current 3D baselines while reducing the need for case-specific retraining. The resulting segmented images preserve physically meaningful descriptors, including fluid saturation, connectivity, and interface morphology, enabling more reliable and rapid analysis of large 3D multiphase images.