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

2026-02-10

AI Summary

This work addresses the limited interpretability of 3D Gaussian Splatting (3DGS), which hinders its deployment in safety-critical domains, and the inability of existing methods to capture voxel-wise consistency among Gaussian primitives. To this end, we propose XSPLAIN, the first prototype-based interpretable framework for 3DGS classification, which delivers intuitive instance-level explanations through representative training samples—effectively conveying “this resembles that.” Our approach integrates a PointNet backbone with voxel aggregation, employs an invertible orthogonal transformation to disentangle feature channels, and generates attribute-aware explanations without altering the model’s decision boundary. In a user study (N=51), 48.4% of participants preferred XSPLAIN’s explanations over baselines, a statistically significant improvement (p<0.001), demonstrating its efficacy in enhancing model transparency and fostering user trust.

Technology Category

• Computer Vision: Interpretability, Explainability, and Transparency
• Machine Learning: Transparent, Interpretable, Explainable ML
• Humans and AI: Explainable AI (XAI) for Human Understanding

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Security and Privacy: Data transparency and provenance
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

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

Problem

• 3D Gaussian Splatting
• interpretability
• explainable AI
• prototype learning
• 3D classification

Innovation

• 3D Gaussian Splatting
• prototype-based interpretability
• ante-hoc XAI
• orthogonal disentanglement
• voxel-aggregated PointNet