Segmenting the Complex and Irregular in Two-Phase Flows: A Real-World Empirical Study with SAM2

TL;DR

This paper demonstrates that a fine-tuned Segment Anything Model v2.1 can accurately segment complex, irregular bubble structures in multiphase flows with minimal annotated data, addressing a longstanding challenge in industrial flow analysis.

Contribution

The study introduces the application of a modern vision foundation model to segment irregular bubbles, showing effective transfer learning with limited annotations in complex flow regimes.

Findings

SAM v2.1 accurately segments non-convex bubbles

Effective with as few as 100 annotated images

Addresses limitations of traditional shape assumptions in segmentation

Abstract

Segmenting gas bubbles in multiphase flows is a critical yet unsolved challenge in numerous industrial settings, from metallurgical processing to maritime drag reduction. Traditional approaches-and most recent learning-based methods-assume near-spherical shapes, limiting their effectiveness in regimes where bubbles undergo deformation, coalescence, or breakup. This complexity is particularly evident in air lubrication systems, where coalesced bubbles form amorphous and topologically diverse patches. In this work, we revisit the problem through the lens of modern vision foundation models. We cast the task as a transfer learning problem and demonstrate, for the first time, that a fine-tuned Segment Anything Model SAM v2.1 can accurately segment highly non-convex, irregular bubble structures using as few as 100 annotated images.