无需人工标注，用单目相机实现高效3D目标检测。
MonoSOWA: Scalable monocular 3D Object detector Without human Annotations
- 通过新提出的局部物体运动模型分离帧间运动源，实现无监督训练。
- 速度比之前方法快700倍，在三个数据集上性能超越已有方法。
- 适合缺乏标注数据的场景，也可作为全监督训练的预训练工具。
从单张RGB图像推断物体的3D位置与朝向是计算机视觉中的基础任务，具有广泛应用。传统3D目标检测方法依赖于激光雷达和大量人工标注，成本高且难以扩展。本文提出一种新方法，仅使用单目相机、无需领域特定的人工标注，即可训练3D目标检测器，使可训练数据量提升数个数量级。该方法引入新的局部物体运动模型，用于分离相邻帧间的物体运动来源；计算效率约为先前工作700倍，并能补偿相机焦距差异，实现多数据集融合。在三个公开数据集上评估，尽管未使用任何人工标签，其性能显著优于此前方法。此外，该方法还展现出作为全监督训练预训练工具的潜力，证明结合多数据集伪标签可达到单数据集人工标签相当的精度。代码与模型已开源。
原文摘要 · Abstract (English)
Inferring object 3D position and orientation from a single RGB camera is a foundational task in computer vision with many important applications. Traditionally, 3D object detection methods are trained in a fully-supervised setup, requiring LiDAR and vast amounts of human annotations, which are laborious, costly, and do not scale well with the ever-increasing amounts of data being captured. We present a novel method to train a 3D object detector from a single RGB camera without domain-specific human annotations, making orders of magnitude more data available for training. The method uses newly proposed Local Object Motion Model to disentangle object movement source between subsequent frames, is approximately 700 times faster than previous work and compensates camera focal length differences to aggregate multiple datasets. The method is evaluated on three public datasets, where despite using no human labels, it outperforms prior work by a significant margin. It also shows its versatility as a pre-training tool for fully-supervised training and shows that combining pseudo-labels from multiple datasets can achieve comparable accuracy to using human labels from a single dataset. The source code and model are available at https://github.com/jskvrna/MonoSOWA.
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。