The image-based 3D object detection task expects that the predicted 3D bounding box has a ``tightness'' projection (also referred to as cuboid), which fits the object contour well on the image while still keeping the geometric attribute on the 3D space, e.g., physical dimension, pairwise orthogonal, etc. These requirements bring significant challenges to the annotation. Simply projecting the Lidar-labeled 3D boxes to the image leads to non-trivial misalignment, while directly drawing a cuboid on the image cannot access the original 3D information. In this work, we propose a learning-based 3D box adaptation approach that automatically adjusts minimum parameters of the 360$^{\circ}$ Lidar 3D bounding box to perfectly fit the image appearance of panoramic cameras. With only a few 2D boxes annotation as guidance during the training phase, our network can produce accurate image-level cuboid annotations with 3D properties from Lidar boxes. We call our method ``you only label once'', which means labeling on the point cloud once and automatically adapting to all surrounding cameras. As far as we know, we are the first to focus on image-level cuboid refinement, which balances the accuracy and efficiency well and dramatically reduces the labeling effort for accurate cuboid annotation. Extensive experiments on the public Waymo and NuScenes datasets show that our method can produce human-level cuboid annotation on the image without needing manual adjustment.
翻译:基于图像的 3D 对象检测任务预计, 预测的 3D 绑定框会有一个“ 紧凑性” 投影( 也称为 cubaboid ), 它符合图像上的对象轮廓, 同时仍然保持 3D 空间上的几何属性, 例如物理维度、 双向正方形等。 这些要求给批注带来重大挑战 。 简单地将 Lidar 标签的 3D 框投射到图像上, 导致非三角错配, 而直接在图像上绘制一个缩略图, 无法访问原始的 3D 信息 。 在这项工作中, 我们提出一个基于学习的 3D 框适应方法, 以自动调整 360 ⁇ circ} 3D 的最小参数, 而同时将3D 3D 框的最小参数保存在 3D 3D 空间上 。 这些要求给批注只给批注了几个 2D 框作为指导 。 我们的网络可以从 Lidar 框中生成准确的图像级线条线条线说明, 3D 属性 。 我们称“ ” 你只标只标记一次不能访问 3D 3D 3D 3D 3D 。 。 。 。, 。 。, 这意味着以 标定一个基于 3D 3D 的标签一次,,,,, 3D 3D 的标签,,, 3D 3D 3D,,,,, 3D 3D 3D 级 级 级 级 级 3D 3D 级, 意味着在 级 级 级 级 级 级 级 级 级 级 级 级 级 级 级 级 级 级 级, 级 级, 级 级, 级, 级, 级, 级 级的 级 级 级 级 级的 级, 级 级 级 级, 级 级 级 级 级 级 级, 级, 级, 级, 级 级 级 级 级 级 级