Rethinking Pseudo-LiDAR Representation
arXiv:2008.04582
Abstract
The recently proposed pseudo-LiDAR based 3D detectors greatly improve the benchmark of monocular/stereo 3D detection task. However, the underlying mechanism remains obscure to the research community. In this paper, we perform an in-depth investigation and observe that the efficacy of pseudo-LiDAR representation comes from the coordinate transformation, instead of data representation itself. Based on this observation, we design an image based CNN detector named Patch-Net, which is more generalized and can be instantiated as pseudo-LiDAR based 3D detectors. Moreover, the pseudo-LiDAR data in our PatchNet is organized as the image representation, which means existing 2D CNN designs can be easily utilized for extracting deep features from input data and boosting 3D detection performance. We conduct extensive experiments on the challenging KITTI dataset, where the proposed PatchNet outperforms all existing pseudo-LiDAR based counterparts. Code has been made available at: https://github.com/xinzhuma/patchnet.
ECCV2020. Supplemental Material attached
References in corpus (8)
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- R-FCN: Object Detection via Region-based Fully Convolutional Networks
- High Quality Monocular Depth Estimation via Transfer Learning
- Pseudo-LiDAR++: Accurate Depth for 3D Object Detection in Autonomous Driving
- Orthographic Feature Transform for Monocular 3D Object Detection
- Monocular 3D Object Detection and Box Fitting Trained End-to-End Using Intersection-over-Union Loss
- Cheaper Pre-training Lunch: An Efficient Paradigm for Object Detection
- Monocular 3D Object Detection with Decoupled Structured Polygon Estimation and Height-Guided Depth Estimation
Cited by in corpus (6)
- Advancing Self-supervised Monocular Depth Learning with Sparse LiDAR
- OCM3D: Object-Centric Monocular 3D Object Detection
- Lidar Point Cloud Guided Monocular 3D Object Detection
- Monocular 3D Object Detection: An Extrinsic Parameter Free Approach
- Aug3D-RPN: Improving Monocular 3D Object Detection by Synthetic Images with Virtual Depth
- Synergy between 3DMM and 3D Landmarks for Accurate 3D Facial Geometry