Multi-Layer Gaussian Splatting for Immersive Anatomy Visualization

TL;DR

This paper introduces a multi-layer Gaussian splatting method for efficient, high-quality immersive 3D visualization of medical scans, enabling interactive exploration on resource-constrained devices.

Contribution

It presents a novel layered Gaussian splatting approach with compression techniques to achieve real-time, interactive medical volume visualization suitable for VR environments.

Findings

Achieves interactive frame rates on mobile VR hardware.

Preserves anatomical detail with adjustable quality.

Enables layer-based exploration and clipping in static models.

Abstract

In medical image visualization, path tracing of volumetric medical data like CT scans produces lifelike three-dimensional visualizations. Immersive VR displays can further enhance the understanding of complex anatomies. Going beyond the diagnostic quality of traditional 2D slices, they enable interactive 3D evaluation of anatomies, supporting medical education and planning. Rendering high-quality visualizations in real-time, however, is computationally intensive and impractical for compute-constrained devices like mobile headsets. We propose a novel approach utilizing GS to create an efficient but static intermediate representation of CT scans. We introduce a layered GS representation, incrementally including different anatomical structures while minimizing overlap and extending the GS training to remove inactive Gaussians. We further compress the created model with clustering across layers. Our approach achieves interactive frame rates while preserving anatomical structures, with quality adjustable to the target hardware. Compared to standard GS, our representation retains some of the explorative qualities initially enabled by immersive path tracing. Selective activation and clipping of layers are possible at rendering time, adding a degree of interactivity to otherwise static GS models. This could enable scenarios where high computational demands would otherwise prohibit using path-traced medical volumes.