Zero-Shot Digital Rock Image Segmentation with a Fine-Tuned Segment Anything Model
This work addresses the need for efficient and accurate segmentation in digital rock physics for oil and gas extraction, but it is incremental as it adapts an existing model to a specific domain.
The researchers tackled the problem of segmenting complex CT and SEM rock images, which is challenging due to low contrast and lack of annotations, by fine-tuning the Segment Anything Model (SAM) to create RockSAM, resulting in significantly enhanced performance and high-quality mask generation for digital rock analysis.
Accurate image segmentation is crucial in reservoir modelling and material characterization, enhancing oil and gas extraction efficiency through detailed reservoir models. This precision offers insights into rock properties, advancing digital rock physics understanding. However, creating pixel-level annotations for complex CT and SEM rock images is challenging due to their size and low contrast, lengthening analysis time. This has spurred interest in advanced semi-supervised and unsupervised segmentation techniques in digital rock image analysis, promising more efficient, accurate, and less labour-intensive methods. Meta AI's Segment Anything Model (SAM) revolutionized image segmentation in 2023, offering interactive and automated segmentation with zero-shot capabilities, essential for digital rock physics with limited training data and complex image features. Despite its advanced features, SAM struggles with rock CT/SEM images due to their absence in its training set and the low-contrast nature of grayscale images. Our research fine-tunes SAM for rock CT/SEM image segmentation, optimizing parameters and handling large-scale images to improve accuracy. Experiments on rock CT and SEM images show that fine-tuning significantly enhances SAM's performance, enabling high-quality mask generation in digital rock image analysis. Our results demonstrate the feasibility and effectiveness of the fine-tuned SAM model (RockSAM) for rock images, offering segmentation without extensive training or complex labelling.