Shao, S., Pei, Z., Chen, W., Liu, Q., Yue, H., & Li, Z. (2024). Sparse Pseudo-LiDAR Depth Assisted Monocular Depth Estimation. IEEE Transactions on Intelligent Vehicles, 9(1), 917–929. https://doi.org/10.1109/tiv.2023.3299935
Abstract:
Monocular depth estimation has attracted extensive
attention and made great progress in recent years. However, the
performance still lags far behind LiDAR-based depth completion
algorithms. This is because the completion algorithms not only utilize
theRGBimage, but also have the prior of sparse depth collected
by LiDAR. To reduce this performance gap, we propose a novel
initiative that incorporates the concept of pseudo-LiDARinto depth
estimation. The pseudo-LiDAR depends only on the camera and
thus achieves a lower cost than LiDAR. To emulate the scan pattern
of LiDAR, geometric sampling and appearance sampling are proposed.
The former measures the vertical and horizontal azimuths
of 3D scene points to establish the geometric correlation. The latter
helps determine which “pseudo-LiDAR rays” return an answer
and which do not. Then, we build a sparse pseudo-LiDAR-based
depth estimation framework. Extensive experiments show that the
proposed method surpasses previous state-of-the-art competitors
on the KITTI, NYU-Depth-v2 and SUN RGB-D datasets.
License type:
Publisher Copyright
Funding Info:
This research / project is supported by the A*STAR - Robotics Horizontal Technology Coordinating Office (HTCO)
Grant Reference no. : C221518005
This work was supported by the National Natural Science Foundation of
China under grant 61620106012.