用形状先验补全稀疏点云，提升自动驾驶3D检测性能
Shape-Prior-Based Point Cloud Completion for Single-Stage Fully Sparse 3D Object Detection
- 通过实例选择模块识别前景点云，忽略背景噪声
- 基于对齐的补全模块，按中心和朝向匹配原型点云填充缺失部分
- 在KITTI数据集上显著提升两类单阶段稀疏检测器性能
单阶段全稀疏3D目标检测器依赖点云数据在自动驾驶场景中检测物体，但点云的稀疏性和不完整性严重制约了检测性能。为此，本文提出一种专为单阶段全稀疏检测器设计的点云补全方法。整个基于形状先验的补全过程包含两个连续步骤：第一步设计新型实例选择模块，可在基线模型未生成候选框时仍准确识别前景物体点云，并有效过滤背景点云；第二步引入基于对齐的点补全模块，将前景点云中心与朝向对齐至原型，再从原型中选取点以填补前景物体缺失部分。在KITTI数据集上，使用两种单阶段全稀疏检测器进行评估，实验结果表明所提方法显著提升检测性能，验证了其有效性和泛化能力。
原文摘要 · Abstract (English)
Single-stage fully sparse 3D object detectors rely on point clouds data to detect objects in autonomous driving scenarios. However, the sparsity and incompleteness of point clouds significantly limit the performance of 3D object detection. To address this issue, this paper proposes a point clouds completion method specifically designed for single-stage fully sparse detectors. The entire shape-prior-based completion process consists of two consecutive steps. In the first step, we design a novel Instance Selection module, which is capable of identifying point clouds corresponding to foreground objects even when the baseline model does not generate proposals, while effectively ignoring the point clouds of background regions. In the second step, we introduce a novel Alignment-Based Point Completion module, which aligns the point clouds of foreground objects with prototypes in terms of both their centers and orientations. Subsequently, points are selected from the prototype to fill in the missing parts of the foreground object. We evaluated our method on two single-stage fully sparse detectors using the KITTI dataset. The experimental results demonstrate that the proposed method significantly improves the detection performance, confirming its effectiveness and generalizability.
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。