.png){kind=icon}
Return
Information-Theoretic Odometry Learning
.png){kind=icon}
OA
AI
DOI：10.1007/s11263-022-01659-9.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
In this paper, we propose a unified information theoretic framework for learning-motivated methods aimed at odometry estimation, a crucial component of many robotics and vision tasks such as navigation and virtual reality where relative camera poses are required in real time. We formulate this problem as optimizing a variational information bottleneck objective function, which eliminates pose-irrelevant information from the latent representation. The proposed framework provides an elegant tool for performance evaluation and understanding in information-theoretic language. Specifically, we bound the generalization errors of the deep information bottleneck framework and the predictability of the latent representation. These provide not only a performance guarantee but also practical guidance for model design, sample collection, and sensor selection. Furthermore, the stochastic latent representation provides a natural uncertainty measure without the needs for extra structures or computations. Experiments on two well-known odometry datasets demonstrate the effectiveness of our method.
Keywords:
Odometry learning
Simultaneous localization and mapping
Information bottleneck
Generalization bound
Journal
IF:
9.3
Papers:
3.9K
Citations:
2.8W
Organization
Cited Papers
ShareSaveEvaluation of qualitative and quantitative data of Y-90 imaging in SPECT/CT and PET/CT phantom studies.png)
PLOS ONEOAAI
PLOS ONEIF0
OAAIShareSaveShareSave
View more