End-to-End Pseudo-LiDAR for Image-Based 3D Object Detection
Research output: Contribution to journal › Conference article › Research › peer-review
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.
Original language | English |
---|---|
Article number | 9157553 |
Journal | Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition |
Pages (from-to) | 5880-5889 |
Number of pages | 10 |
ISSN | 1063-6919 |
DOIs | |
Publication status | Published - 2020 |
Externally published | Yes |
Event | 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020 - Virtual, Online, United States Duration: 14 Jun 2020 → 19 Jun 2020 |
Conference
Conference | 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020 |
---|---|
Country | United States |
City | Virtual, Online |
Period | 14/06/2020 → 19/06/2020 |
Bibliographical note
Funding Information:
This research is supported by grants from the National Science Foundation NSF (III-1618134, III-1526012, IIS-1149882, IIS-1724282, and TRIPODS-1740822), the Office of Naval Research DOD (N00014-17-1-2175), the Bill and Melinda Gates Foundation, and the Cornell Center for Materials Research with funding from the NSF MRSEC program (DMR-1719875). We are thankful for generous support by Zillow and SAP America Inc.
Publisher Copyright:
© 2020 IEEE.
ID: 301822796