Learning Holistic Geometric Representations for Monocular 3D Object Detection
Yinmin Zhang1, Xinzhu Ma2, Shuai Yi1, Jun Hou1, Zhihui Wang3, Wanli Ouyang2 Dan Xu4, 1SenseTime Research, 2The University of Sydney, 3Dalian University of Technology 4The Hong Kong University of Science and Technology, {zhangyinmin, yishuai, {xinzhu.ma,
Abstract
As a crucial task of autonomous driving, 3D object detection has made significant progress in recent years. However, monocular 3D object detection remains a challenging problem due to the unsatisfactory performance in depth estimation. Most existing monocular methods typically directly regress the depth, while ignoring essential relationships between the depth and various geometric elements (e.g. bounding box sizes, 3D object dimensions, and object poses). In this paper, we propose to learn geometry-guided depth estimation with projective modeling to advance monocular 3D object detection. Specifically, a principled geometry formula with projective modeling of 2D and 3D depth predictions in the monocular 3D object detection network is devised. We further implement and embed the proposed formula to enable geometry-aware deep representation learning, allowing effective 2D and 3D interactions for boosting the depth estimation. Moreover, we provide a strong baseline through addressing substantial misalignment between 2D annotation and projected boxes to ensure robust learning with the proposed holistic geometric formula. Experiments on the KITTI dataset show that our method remarkably i
中文速览
单目摄像头做自动驾驶中的三维目标检测，最大的拦路虎就是深度估计不准——现有方法大多直接回归深度值，却忽略了深度与2D边界框大小、3D物体尺寸、物体姿态和位置之间的几何关系。本文提出一套基于投影建模的整体几何公式，把上述多种2D/3D几何要素统一纳入深度计算，并将该公式封装成可端到端训练的网络模块，让模型在特征学习层面就能感知几何约束，而非仅靠后处理修正。此外，作者还专门处理了2D标注框与3D投影框之间的严重错位问题，构建了一个更可靠的训练基线。在KITTI基准上，该方法无需额外数据，在中等难度汽车检测指标上比此前最优单目方法提升了2.80%，验证了显式几何建模对突破单目3D检测瓶颈的重要价值。
原文 arXiv:2107.13931;中英对照 + 大白话阅读 https://aha.fim.ai/paper/2107.13931v2