将3D高斯点云属性映射到点云，提升边界感知的分割精度
G2P: Gaussian-to-Point Attribute Alignment for Boundary-Aware 3D Segmentation
- 通过点对点对应关系对齐高斯属性与原始几何结构
- 在复杂场景中实现更精准的边界定位，准确率显著提升
- 无需2D预训练或语言监督，适合高精度3D分割任务
点云分割对于三维场景理解至关重要。然而，稀疏且不规则的点分布提供的外观信息有限，仅依赖几何特征难以区分形状相似但外观不同的物体（如颜色、纹理、材质）。本文提出高斯到点（G2P）方法，将3D高斯泼溅中的属性迁移至点云，实现更具区分性且外观一致的分割。G2P通过建立点级对应关系，解决优化后高斯与原始点几何之间的错位问题；通过蒸馏透明度导出的可见性线索，缓解现有模型受限于几何模糊的问题；同时利用高斯尺度属性，在复杂三维场景中实现精确的边界定位。大量实验表明，该方法在标准基准上表现优异，并在几何挑战性强的类别上取得显著提升，且分割流程中无需预训练2D特征或语言监督。
原文摘要 · Abstract (English)
Point cloud segmentation is critical for 3D scene understanding. However, sparse and irregular point distributions provide limited appearance evidence, making geometry-only features insufficient to distinguish objects with similar shapes but distinct appearances e.g., color, texture, and material. We propose Gaussian-to-Point (G2P), which transfers Gaussian attributes from 3D Gaussian Splatting to point clouds for more discriminative and appearance-consistent segmentation. Our G2P addresses the misalignment between optimized Gaussians and original point geometry by establishing point-wise correspondences. By distilling opacity-derived visibility cues, we mitigate the geometric ambiguity that limits existing models. Additionally, Gaussian scale attributes enable precise boundary localization in complex 3D scenes. Extensive experiments demonstrate that our approach achieves competitive performance on standard benchmarks and shows notable improvements on geometrically challenging classes, without pretrained 2D features or language supervision in our segmentation pipeline.
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。