.png){kind=icon}
.png){kind=icon}
Return
HDVO: Hybrid Dense Direct Visual Odometry
.png){kind=icon}
PRE
AI
Z
E
P
DOI：10.1109/tiv.2026.3708447.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Dense direct visual odometry (DDVO) is a well-known robust model-based visual odometry method, that computes robot self-localization with visual data. However, to obtain a metric localization depth information is needed, which is not available in most applications, especially in outdoor scenarios. For this reason, we focus on a hybrid dense direct visual odometry (HDVO) that combines a model-based localization module and a data-based stereo depth estimation module. Since depth is estimated from a stereo sensor, the proposed HDVO can achieve better localization performance than methods using only monocular RGB data. Moreover, the learning part of HDVO is optimized with the photometric loss of DDVO without any depth supervision signal. For this loss, occlusion and low-texture will affect the optimization convergence. This paper investigates a binary mask based on stereo-temporal consistency to address the occlusion problem, along with another binary mask based on local patch consistency to solve the low-texture problem. Finally, it is shown that HDVO can achieve a significant advantage in terms of both inference speed and odometry error on public benchmarks.
Keywords:
Visual odometry
hybrid AI method
data-based algortihm
model-based algorithm
computer vision
robotics
autonomous driving
Journal
I
IF:
14.3
Papers:
1.2K
Citations:
1.2W
Organization
Cited Papers