当前位置: X-MOL 学术arXiv.cs.CV › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
End-to-End Pseudo-LiDAR for Image-Based 3D Object Detection
arXiv - CS - Computer Vision and Pattern Recognition Pub Date : 2020-04-07 , DOI: arxiv-2004.03080
Rui Qian, Divyansh Garg, Yan Wang, Yurong You, Serge Belongie, Bharath Hariharan, Mark Campbell, Kilian Q. Weinberger, Wei-Lun Chao

Reliable and accurate 3D object detection is a necessity for safe autonomous driving. Although LiDAR sensors can provide accurate 3D point cloud estimates of the environment, they are also prohibitively expensive for many settings. Recently, the introduction of pseudo-LiDAR (PL) has led to a drastic reduction in the accuracy gap between methods based on LiDAR sensors and those based on cheap stereo cameras. PL combines state-of-the-art deep neural networks for 3D depth estimation with those for 3D object detection by converting 2D depth map outputs to 3D point cloud inputs. However, so far these two networks have to be trained separately. In this paper, we introduce a new framework based on differentiable Change of Representation (CoR) modules that allow the entire PL pipeline to be trained end-to-end. The resulting framework is compatible with most state-of-the-art networks for both tasks and in combination with PointRCNN improves over PL consistently across all benchmarks -- yielding the highest entry on the KITTI image-based 3D object detection leaderboard at the time of submission. Our code will be made available at https://github.com/mileyan/pseudo-LiDAR_e2e.

中文翻译:

用于基于图像的 3D 对象检测的端到端伪激光雷达

可靠且准确的 3D 物体检测是安全自动驾驶的必要条件。尽管 LiDAR 传感器可以提供环境的准确 3D 点云估计,但对于许多设置而言,它们的成本也高得惊人。最近,伪 LiDAR (PL) 的引入导致基于 LiDAR 传感器的方法与基于廉价立体相机的方法之间的精度差距急剧缩小。PL 通过将 2D 深度图输出转换为 3D 点云输入,将最先进的用于 3D 深度估计的深度神经网络与用于 3D 对象检测的深度神经网络相结合。然而,到目前为止,这两个网络必须分开训练。在本文中,我们引入了一个基于可微表示变化 (CoR) 模块的新框架,该框架允许端到端地训练整个 PL 管道。由此产生的框架与大多数最先进的网络兼容,并且与 PointRCNN 相结合,在所有基准测试中始终优于 PL——在 KITTI 基于图像的 3D 对象检测排行榜上取得了最高的成绩。提交。我们的代码将在 https://github.com/mileyan/pseudo-LiDAR_e2e 上提供。
更新日期:2020-05-15
down
wechat
bug