.png){kind=icon}
返回
Sparse Pseudo-LiDAR Depth Assisted Monocular Depth Estimation
.png){kind=icon}
PRE
AI
DOI：10.1109/TIV.2023.3299935.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
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 the RGB image, 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.
Keyword:
Laser radar
Estimation
Azimuth
Three-dimensional displays
Cameras
Intelligent vehicles
Point cloud compression
Monocular Depth Estimation
LiDAR
Pseudo-LiDAR
期刊
I
IF:
14.3
论文数:
1.2K
被引数:
1.2W
机构
引用论文
.png){kind=icon}
Inflexibility of mental planning: A characteristic disorder with prefrontal lobe lesions?心理计划的僵化: 前额叶病变的特征性障碍？
PREAI
分享收藏分享收藏
分享收藏
查看更多内容