Log In Sign Up

Rethinking Pseudo-LiDAR Representation

by   Xinzhu Ma, et al.

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:


page 12

page 14

page 21


Pseudo-Stereo for Monocular 3D Object Detection in Autonomous Driving

Pseudo-LiDAR 3D detectors have made remarkable progress in monocular 3D ...

Progressive Coordinate Transforms for Monocular 3D Object Detection

Recognizing and localizing objects in the 3D space is a crucial ability ...

Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Driving

3D object detection is an essential task in autonomous driving. Recent t...

MonoDistill: Learning Spatial Features for Monocular 3D Object Detection

3D object detection is a fundamental and challenging task for 3D scene u...

RTS3D: Real-time Stereo 3D Detection from 4D Feature-Consistency Embedding Space for Autonomous Driving

Although the recent image-based 3D object detection methods using Pseudo...

Towards Safe, Real-Time Systems: Stereo vs Images and LiDAR for 3D Object Detection

As object detectors rapidly improve, attention has expanded past image-o...

Demystifying Pseudo-LiDAR for Monocular 3D Object Detection

Pseudo-LiDAR-based methods for monocular 3D object detection have genera...