XSPLAIN: XAI-enabling Splat-based Prototype Learning for Attribute-aware INterpretability
This addresses the problem of interpretability for users in critical domains relying on 3DGS, offering a novel method for attribute-aware transparency.
The paper tackles the lack of interpretability in 3D Gaussian Splatting (3DGS) classification by introducing XSPLAIN, an ante-hoc prototype-based framework that provides intuitive explanations without degrading performance, with a user study (N=51) showing participants preferred XSPLAIN explanations 48.4% of the time, significantly outperforming baselines (p<0.001).
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