提出轻量级超点分割框架，实现实时3D语义分割
EZ-SP: Fast and Lightweight Superpoint-Based 3D Segmentation
- 基于可学习的全GPU超点划分，速度比之前快13倍
- 仅需不到2MB显存，支持数百万点云实时推理
- 在多个数据集上达到顶尖模型精度，参数减少120倍
基于超点的3D语义分割方案提供了点或体素方法的高效替代，但常受制于其依赖CPU的划分步骤。本文提出一种可学习的全GPU划分算法，生成在几何与语义上一致的超点，速度比现有方法快13倍。该模块参数少于60k，采用可微分代理损失，训练时间低于20分钟，无需手工特征。结合轻量级超点分类器，整个流程仅需小于2MB显存，可扩展至数百万点云场景，并支持实时推理。在三个领域（室内扫描S3DIS、自动驾驶KITTI-360、航拍LiDAR DALES）上，相比点基最优模型，实现72倍更快推理和120倍更少参数，同时保持相当精度。代码与预训练模型见github.com/drprojects/superpoint_transformer。
原文摘要 · Abstract (English)
Superpoint-based pipelines provide an efficient alternative to point- or voxel-based 3D semantic segmentation, but are often bottlenecked by their CPU-bound partition step. We propose a learnable, fully GPU partitioning algorithm that generates geometrically and semantically coherent superpoints 13$\times$ faster than prior methods. Our module is compact (under 60k parameters), trains in under 20 minutes with a differentiable surrogate loss, and requires no handcrafted features. Combine with a lightweight superpoint classifier, the full pipeline fits in $<$2 MB of VRAM, scales to multi-million-point scenes, and supports real-time inference. With 72$\times$ faster inference and 120$\times$ fewer parameters, EZ-SP matches the accuracy of point-based SOTA models across three domains: indoor scans (S3DIS), autonomous driving (KITTI-360), and aerial LiDAR (DALES). Code and pretrained models are accessible at github.com/drprojects/superpoint_transformer.
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。