XSPLAIN: XAI-enabling Splat-based Prototype Learning for Attribute-aware INterpretability

TL;DR

XSPLAIN introduces a prototype-based interpretability framework for 3D Gaussian Splatting, enabling intuitive explanations grounded in training examples without sacrificing classification accuracy.

Contribution

It is the first ante-hoc interpretability method for 3DGS, using a novel feature disentanglement technique and prototype explanations to improve transparency.

Findings

User study shows 48.4% preference for XSPLAIN explanations

XSPLAIN maintains classification performance while providing interpretability

Significant user trust improvement over baselines (p<0.001)

Abstract

3D Gaussian Splatting (3DGS) has rapidly become a standard for high-fidelity 3D reconstruction, yet its adoption in multiple critical domains is hindered by the lack of interpretability of the generation models as well as classification of the Splats. While explainability methods exist for other 3D representations, like point clouds, they typically rely on ambiguous saliency maps that fail to capture the volumetric coherence of Gaussian primitives. We introduce XSPLAIN, the first ante-hoc, prototype-based interpretability framework designed specifically for 3DGS classification. Our approach leverages a voxel-aggregated PointNet backbone and a novel, invertible orthogonal transformation that disentangles feature channels for interpretability while strictly preserving the original decision boundaries. Explanations are grounded in representative training examples, enabling intuitive ``this looks like that'' reasoning without any degradation in classification performance. A rigorous user study (N=51) demonstrates a decisive preference for our approach: participants selected XSPLAIN explanations 48.4\% of the time as the best, significantly outperforming baselines $(p<0.001)$, showing that XSPLAIN provides transparency and user trust. The source code for this work is available at: https://github.com/Solvro/ml-splat-xai