arxiv.org·2026/10/26
为什么重要 提供首个真实多模态 3D 异常分割与开放集基准，为自动驾驶感知安全部署提供评测依据。
近期，3D 语义分割的进展显著提升了自动驾驶场景理解。然而，现有方法通常在闭集假设下开发，并在标准驾驶条件下评估，所有类别都事先已知。在真实世界驾驶中，自动驾驶车辆不可避免地会遇到之前未见过的物体，这使得闭集感知不足以实现安全部署。
为解决该挑战，我们提出 DriveOSS，据我们所知，它是首个专门为 3D 异常分割和开放集语义分割设计的真实世界多模态数据集与基准。它包含 12,661 帧同步标注帧，使用六个环绕 RGB 相机、一个 128 线 LiDAR 和一个 GPS/IMU 单元采集。该数据集包含 52 个真实驾驶场景，涵盖晴天、夜间、多云、雨天和雪天条件，并划分为 ID（分布内）和 OOD（分布外）子集。
ID 场景仅包含已知类别并用于训练，而 OOD 场景额外包含被标注为异常类的未知物体，用于验证和测试。大量实验表明，未见物体对当前 3D 感知系统仍是重大挑战。数据集、基准协议和代码可在 https://github.com/chrisyan/DriveOSS 获取。
Recent advances in 3D semantic segmentation have significantly improved scene understanding in autonomous driving.
However, existing methods are typically developed under a closed-set assumption and evaluated under standard driving conditions, where all categories are known in advance.
In real-world driving, autonomous vehicles inevitably encounter previously unseen objects, making closed-set perception insufficient for safe deployment.
To address this challenge, we introduce DriveOSS, which, to the best of our knowledge, is the first real-world multimodal dataset and benchmark specifically designed for 3D anomaly segmentation and open-set semantic segmentation.
It contains 12,661 synchronized and annotated frames captured using six surround-view RGB cameras, a 128-beam LiDAR, and a GPS/IMU unit.
The dataset comprises 52 real-world driving scenes collected under clear, nighttime, cloudy, rainy, and snowy conditions and is organized into ID (in-distribution) and OOD (out-of-distribution) subsets.
The ID scenes contain only known classes and are used for training, whereas the OOD scenes additionally contain unknown objects annotated as the outlier class and are used for validation and testing.
Extensive experiments show that unseen objects remain a major challenge for current 3D perception systems.
The dataset, benchmark protocols, and code are available at https://github.com/chrisyan/DriveOSS.
原版排版与图表 · 手机无法内嵌时可在浏览器打开。PDF 插件内选文不能传给网页助手。