The proposal of Pseudo-Lidar representation has
significantly narrowed the gap between visual-based and active
Lidar-based 3D object detection. However, current researches exclusively focus on pushing the accuracy improvement of PseudoLidar by taking the advantage of complex and time-consuming
neural networks. Seldom explore the profound characteristics
of Pseudo-Lidar representation to obtain the promoting opportunities. In this paper, we dive deep into the pseudo Lidar
representation and argue that the performance of 3D object
detection is not fully dependent on the high precision stereo
depth estimation. We demonstrate that even for the unreliable
depth estimation, with proper data processing and refining, it
can achieve comparable 3D object detection accuracy. With
this finding, we further show the possibility that utilizing fast
but inaccurate stereo matching algorithms in the Pseudo-Lidar
system to achieve low latency responsiveness. In the experiments,
we develop a system with a less powerful stereo matching
predictor and adopt the proposed refinement schemes to improve
the accuracy. The evaluation on the KITTI benchmark shows that
the presented system achieves competitive accuracy to the stateof-the-art approaches with only 23 ms computing, showing it is
a suitable candidate for deploying to real car-hold applications.
«
The proposal of Pseudo-Lidar representation has
significantly narrowed the gap between visual-based and active
Lidar-based 3D object detection. However, current researches exclusively focus on pushing the accuracy improvement of PseudoLidar by taking the advantage of complex and time-consuming
neural networks. Seldom explore the profound characteristics
of Pseudo-Lidar representation to obtain the promoting opportunities. In this paper, we dive deep into the pseudo Lidar
representation and...
»