让3D高斯点云分类可解释，通过原型学习实现直观推理。
XSPLAIN: XAI-enabling Splat-based Prototype Learning for Attribute-aware INterpretability
- 基于体素点云的PointNet和可逆正交变换，解耦特征通道以提升可解释性。
- 用户研究显示48.4%参与者首选该方法，显著优于基线（p<0.001）。
- 适用于需要透明决策的3D重建、医学影像等关键领域。
3D高斯点阵（3DGS）已成为高保真三维重建的标准，但其在多个关键领域的应用受限于生成模型的不可解释性及点阵分类问题。尽管已有针对其他3D表示（如点云）的可解释性方法，但通常依赖模糊的显著性图，无法捕捉高斯原语的体积一致性。本文提出XSPLAIN，首个面向3DGS分类的前向原型可解释框架。该方法采用体素聚合的PointNet主干网络与新颖的可逆正交变换，解耦特征通道以增强可解释性，同时严格保留原始决策边界。解释基于代表性训练样本，支持直观的“此像彼”推理，且不降低分类性能。一项严格的用户研究（N=51）表明，参与者有48.4%选择XSPLAIN的解释为最佳，显著优于基线（p<0.001），证明其能有效提升透明度与用户信任。代码已开源：https://github.com/Solvro/ml-splat-xai。
原文摘要 · Abstract (English)
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
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。