Abstract
Annotating 3D data remains a costly bottleneck for 3D object detection, motivating the development of weakly supervised annotation methods that rely on more accessible 2D box annotations. However, relying solely on 2D boxes introduces projection ambiguities since a single 2D box can correspond to multiple valid 3D poses. Furthermore, partial object visibility under a single viewpoint setting makes accurate 3D box estimation difficult. We propose MVAT, a novel framework that leverages temporal multi-view present in sequential data to address these challenges. Our approach aggregates object-centric point clouds across time to build 3D object representations as dense and complete as possible. A Teacher-Student distillation paradigm is employed: The Teacher network learns from single viewpoints but targets are derived from temporally aggregated static objects. Then the Teacher generates high quality pseudo-labels that the Student learns to predict from a single viewpoint for both static and moving objects. The whole framework incorporates a multi-view 2D projection loss to enforce consistency between predicted 3D boxes and all available 2D annotations. Experiments on the nuScenes and Waymo Open datasets demonstrate that MVAT achieves state-of-the-art performance for weakly supervised 3D object detection, significantly narrowing the gap with fully supervised methods without requiring any 3D box annotations. % \footnote{Code available upon acceptance} Our code is available in our public repository (\href{this https URL}{code}).
Abstract (translated)
标注3D数据仍然是3D物体检测中的一个高成本瓶颈，这促使了开发依赖于更易获取的2D框注释的弱监督标注方法的发展。然而，仅依赖2D框会导致投影歧义问题，因为单一的2D框可以对应多个有效的3D姿态。此外，在单视点设置下，部分物体可见性使得准确估计3D边界框变得困难。我们提出了一种新的框架MVAT（多视角时序聚合），利用序列数据中的时间多视角特性来解决这些问题。我们的方法通过跨时间聚集以对象为中心的点云来构建尽可能密集和完整的3D物体表示。 本研究采用了教师-学生蒸馏范式：教师网络从单视点学习，但目标是从时间上聚合后的静态物体中得出。然后，教师生成高质量的伪标签，供学生在单一视角下进行预测，用于静态和移动物体。整个框架整合了一个多视角2D投影损失函数，以确保预测的3D边界框与所有可用的2D注释之间的一致性。 在nuScenes和Waymo Open数据集上的实验表明，MVAT实现了弱监督条件下3D物体检测的最佳性能，并且显著缩小了与完全监督方法之间的差距，同时无需任何3D框标注。我们的代码可在公共存储库中获取（\href{this https URL}{code}）。
URL
https://arxiv.org/abs/2509.07507
