稀疏标注下提升单目3D目标检测精度，通过道路增强与原型过滤实现。
MonoSAOD: Monocular 3D Object Detection with Sparsely Annotated Label
- 利用道路区域增强稀疏标注的物体补丁，保持3D几何一致性
- 通过原型相似性与深度不确定性筛选高质量伪标签
- 适用于标注成本高的真实场景，适合自动驾驶感知研究
单目3D目标检测在密集标注数据集上表现优异，但在仅部分物体标注的稀疏标注场景下性能下降，而此类场景在现实中普遍存在。为应对这一挑战，本文提出新框架MonoSAOD，包含两个核心模块：首先，提出道路感知补丁增强（RAPA），将稀疏标注的物体补丁增强到道路区域，同时保持3D几何一致性；其次，提出基于原型的过滤（PBF），通过原型相似性和深度不确定性筛选高质量伪标签，维护全局2D RoI特征原型，选择与原型一致且深度估计可靠的预测。训练策略结合几何保持增强与原型引导伪标签，实现稀疏监督下的鲁棒检测。大量实验验证了方法的有效性。代码已开源。
原文摘要 · Abstract (English)
Monocular 3D object detection has achieved impressive performance on densely annotated datasets. However, it struggles when only a fraction of objects are labeled due to the high cost of 3D annotation. This sparsely annotated setting is common in real-world scenarios where annotating every object is impractical. To address this, we propose a novel framework for sparsely annotated monocular 3D object detection with two key modules. First, we propose Road-Aware Patch Augmentation (RAPA), which leverages sparse annotations by augmenting segmented object patches onto road regions while preserving 3D geometric consistency. Second, we propose Prototype-Based Filtering (PBF), which generates high-quality pseudo-labels by filtering predictions through prototype similarity and depth uncertainty. It maintains global 2D RoI feature prototypes and selects pseudo-labels that are both feature-consistent with learned prototypes and have reliable depth estimates. Our training strategy combines geometry-preserving augmentation with prototype-guided pseudo-labeling to achieve robust detection under sparse supervision. Extensive experiments demonstrate the effectiveness of the proposed method. The source code is available at https://github.com/VisualAIKHU/MonoSAOD .
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。