直接从点云中检测3D曲线，支持多种曲线类型统一输出。
PI3DETR: Parametric Instance Detection of 3D Point Cloud Edges With a Geometry-Aware 3DETR
- 基于3DETR改进，引入几何感知匹配与专用损失函数。
- 在ABC数据集上达新SOTA，支持立方贝塞尔、圆弧等多类曲线。
- 对噪声和采样密度变化鲁棒，适合真实激光雷达场景。
我们提出PI3DETR，一种端到端框架，可直接从原始点云中预测3D参数化曲线实例，无需中间表示或多阶段处理。在3DETR基础上，模型引入几何感知匹配策略和专用损失函数，实现单次前向传播中对不同参数化曲线类型（包括立方贝塞尔曲线、线段、圆、圆弧）的统一检测。可选后处理步骤可在不增加复杂度的前提下进一步优化预测。该设计提升了对噪声和采样密度变化的鲁棒性，解决了真实世界激光雷达与3D传感中的关键挑战。PI3DETR在ABC数据集上达到新SOTA，并有效泛化至真实传感器数据，为3D边缘与曲线估计提供简单而强大的解决方案。
原文摘要 · Abstract (English)
We present PI3DETR, an end-to-end framework that directly predicts 3D parametric curve instances from raw point clouds, avoiding the intermediate representations and multi-stage processing common in prior work. Extending 3DETR, our model introduces a geometry-aware matching strategy and specialized loss functions that enable unified detection of differently parameterized curve types, including cubic Bézier curves, line segments, circles, and arcs, in a single forward pass. Optional post-processing steps further refine predictions without adding complexity. This streamlined design improves robustness to noise and varying sampling densities, addressing critical challenges in real world LiDAR and 3D sensing scenarios. PI3DETR sets a new state-of-the-art on the ABC dataset and generalizes effectively to real sensor data, offering a simple yet powerful solution for 3D edge and curve estimation.
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。