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

2026-04-29

AI Summary

This work addresses the limited generalization of existing 3D segmentation methods on multiphase pore-scale X-ray images of rocks, which often require extensive retraining when rock type, fluid distribution, or scanning conditions change. To overcome this, the study proposes a parameter-efficient 3D segmentation framework that integrates the Segment Anything Model (SAM) with the Mamba architecture for the first time. The approach freezes the SAM encoder to extract universal features and combines it with a Mamba-based voxel context modeling module and cross-scale feature interaction to enable efficient and generalizable segmentation. Evaluated on multi-condition datasets of sandstone and carbonate rocks, the method matches or surpasses current baselines while accurately preserving key physical metrics such as fluid saturation, connectivity, and interface morphology, substantially reducing the need for retraining.

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.

Problem

• 3D segmentation
• multiphase pore-scale images
• generalizable segmentation
• X-ray imaging
• fluid saturation

Innovation

• SAMamba3D
• 3D segmentation
• foundation model adaptation
• Mamba-based context modeling
• pore-scale imaging