Pixel-Wise Prediction based Visual Odometry via Uncertainty Estimation

This paper introduces pixel-wise prediction based visual odometry (PWVO), which is a dense prediction task that evaluates the values of translation and rotation for every pixel in its input observations. PWVO employs uncertainty estimation to identify the noisy regions in the input observations, and...

Full description

Saved in:
Bibliographic Details
Main Authors: Chen, Hao-Wei, Liao, Ting-Hsuan, Yang, Hsuan-Kung, Lee, Chun-Yi
Format: Conference Proceeding
Language:English
Subjects:
Estimation
Noise measurement
pixel-wised predictions
Task analysis
Training
Training data
Uncertainty
uncertainty estimation
Visual odometry
Visualization
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper introduces pixel-wise prediction based visual odometry (PWVO), which is a dense prediction task that evaluates the values of translation and rotation for every pixel in its input observations. PWVO employs uncertainty estimation to identify the noisy regions in the input observations, and adopts a selection mechanism to integrate pixel-wise predictions based on the estimated uncertainty maps to derive the final translation and rotation. In order to train PWVO in a comprehensive fashion, we further develop a data generation workflow for generating synthetic training data. The experimental results show that PWVO is able to deliver favorable results. In addition, our analyses validate the effectiveness of the designs adopted in PWVO, and demonstrate that the uncertainty maps estimated by PWVO is capable of capturing the noises in its input observations.
ISSN:2642-9381
DOI:10.1109/WACV56688.2023.00255