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

arXiv cs.CV / 5/5/2026

📰 NewsIdeas & Deep AnalysisModels & Research

共有:

Key Points

The paper addresses a key limitation of existing 3D pore-scale image segmentation methods, which often require retraining or heavy fine-tuning when rock types, fluids, scanners, or acquisition conditions change.
It introduces SAMamba3D, a parameter-efficient framework that adapts a mostly frozen 2D Segment Anything (SAM) encoder to 3D segmentation using Mamba-based volumetric context modeling and progressive cross-scale feature interaction.
Experiments on sandstone and carbonate datasets with varying fluids, wettability, and scanning conditions show that SAMamba3D matches or outperforms current 3D baselines.
The approach aims to produce physically meaningful segmentation outputs (e.g., fluid saturation, connectivity, and interfacial morphology) to support more reliable and faster analysis of large 3D multiphase 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.