FocalFormer3D：专注于3D物体检测中的困难实例

摘要

在自动驾驶中，三维物体检测中的假阴性（FN），例如漏检行人、车辆或其他障碍物，可能导致潜在危险情况。尽管致命，但这个问题在许多当前的三维检测方法中研究不足。在这项工作中，我们提出了Hard Instance Probing（HIP），这是一个通用流程，以多阶段方式识别FN，并引导模型专注于挖掘困难实例。对于三维物体检测，我们将这种方法实例化为FocalFormer3D，这是一个简单而有效的检测器，擅长挖掘困难物体并提高预测召回率。FocalFormer3D具有多阶段查询生成，以发现困难物体，并具有盒级变换器解码器，以有效区分大量物体候选。在nuScenes和Waymo数据集上的实验结果验证了FocalFormer3D的卓越性能。这种优势在激光雷达和多模态设置中的检测和跟踪方面表现出色。值得注意的是，FocalFormer3D在nuScenes检测基准上实现了70.5 mAP和73.9 NDS，而nuScenes跟踪基准显示72.1 AMOTA，在nuScenes激光雷达排行榜上均排名第一。我们的代码可在https://github.com/NVlabs/FocalFormer3D 获取。

English

False negatives (FN) in 3D object detection, {\em e.g.}, missing predictions of pedestrians, vehicles, or other obstacles, can lead to potentially dangerous situations in autonomous driving. While being fatal, this issue is understudied in many current 3D detection methods. In this work, we propose Hard Instance Probing (HIP), a general pipeline that identifies FN in a multi-stage manner and guides the models to focus on excavating difficult instances. For 3D object detection, we instantiate this method as FocalFormer3D, a simple yet effective detector that excels at excavating difficult objects and improving prediction recall. FocalFormer3D features a multi-stage query generation to discover hard objects and a box-level transformer decoder to efficiently distinguish objects from massive object candidates. Experimental results on the nuScenes and Waymo datasets validate the superior performance of FocalFormer3D. The advantage leads to strong performance on both detection and tracking, in both LiDAR and multi-modal settings. Notably, FocalFormer3D achieves a 70.5 mAP and 73.9 NDS on nuScenes detection benchmark, while the nuScenes tracking benchmark shows 72.1 AMOTA, both ranking 1st place on the nuScenes LiDAR leaderboard. Our code is available at https://github.com/NVlabs/FocalFormer3D.

FocalFormer3D：专注于3D物体检测中的困难实例

FocalFormer3D : Focusing on Hard Instance for 3D Object Detection

摘要

Support