用点云引导实现高精度实时多对象分割，解决传统方法初始化慢、视角不一致问题。
PointGauss: Point Cloud-Guided Multi-Object Segmentation for Gaussian Splatting
- 通过点云分割驱动的管线直接解析高斯原始，1分钟内生成3D实例掩码。
- 多视角mIoU提升1.89%至31.78%，计算效率优于现有方法。
- 适合需要快速、准确3D多物体分割的研究与应用，如机器人感知。
我们提出PointGauss，一种面向高斯点绘表示的实时多对象分割新框架。不同于现有方法在初始化耗时长且多视角一致性差的问题，本方法通过点云分割驱动的流水线，高效实现3D分割。核心创新包括：(1) 基于点云的高斯原始解码器，可在1分钟内生成3D实例掩码；(2) GPU加速的2D掩码渲染系统，确保多视角一致性。大量实验表明，相比先前最先进方法，多视角mIoU提升1.89%至31.78%，同时保持优异计算效率。为弥补现有基准的局限性（单对象、3D评估不一致、数据规模小、覆盖不全），我们构建DesktopObjects-360——一个全新的辐射场3D分割数据集，具备：(1) 复杂多对象场景，(2) 全局一致的2D标注，(3) 超过27,000个2D掩码的大规模训练数据，(4) 完整360°覆盖，(5) 3D评估掩码。
原文摘要 · Abstract (English)
We introduce PointGauss, a novel point cloud-guided framework for real-time multi-object segmentation in Gaussian Splatting representations. Unlike existing methods that suffer from prolonged initialization and limited multi-view consistency, our approach achieves efficient 3D segmentation by directly parsing Gaussian primitives through a point cloud segmentation-driven pipeline. The key innovation lies in two aspects: (1) a point cloud-based Gaussian primitive decoder that generates 3D instance masks within 1 minute, and (2) a GPU-accelerated 2D mask rendering system that ensures multi-view consistency. Extensive experiments demonstrate significant improvements over previous state-of-the-art methods, achieving performance gains of 1.89 to 31.78% in multi-view mIoU, while maintaining superior computational efficiency. To address the limitations of current benchmarks (single-object focus, inconsistent 3D evaluation, small scale, and partial coverage), we present DesktopObjects-360, a novel comprehensive dataset for 3D segmentation in radiance fields, featuring: (1) complex multi-object scenes, (2) globally consistent 2D annotations, (3) large-scale training data (over 27 thousand 2D masks), (4) full 360° coverage, and (5) 3D evaluation masks.
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。