Towards data-driven filters in Paraview

TL;DR

This paper introduces a novel approach to integrate pre-trained machine learning models as data-driven filters within Paraview, enabling advanced analysis like segmentation and classification in scientific visualization.

Contribution

It extends Paraview with plugins that allow loading and applying pre-trained ML models as filters, bridging visualization and machine learning for enhanced data analysis.

Findings

Successfully integrated ML models as filters in Paraview

Demonstrated segmentation and classification use cases

Showcased technical feasibility for future complex analysis

Abstract

Recent progress in scientific visualization has expanded the scope of visualization from being merely a way of presentation to an analysis and discovery tool. A given visualization result is usually generated by applying a series of transformations or filters to the underlying data. Nowadays, such filters use deterministic algorithms to process the data. In this work, we aim at extending this methodology towards data-driven filters, thus filters that expose the abilities of pre-trained machine learning models to the visualization system. The use of such data-driven filters is of particular interest in fields like segmentation, classification, etc., where machine learning models regularly outperform existing algorithmic approaches. To showcase this idea, we couple Paraview, the well-known flow visualization tool, with PyTorch, a deep learning framework. Paraview is extended by plugins that allow users to load pre-trained models of their choice in the form of newly developed filters. The filters transform the input data by feeding it into the model and then provide the model's output as input to the remaining visualization pipeline. A series of simplistic use cases for segmentation and classification on image and fluid data is presented to showcase the technical applicability of such data-driven transformations in Paraview for future complex analysis tasks.