DeepAI AI Chat
Log In Sign Up

Learning monocular visual odometry with dense 3D mapping from dense 3D flow

by   Cheng Zhao, et al.

This paper introduces a fully deep learning approach to monocular SLAM, which can perform simultaneous localization using a neural network for learning visual odometry (L-VO) and dense 3D mapping. Dense 2D flow and a depth image are generated from monocular images by sub-networks, which are then used by a 3D flow associated layer in the L-VO network to generate dense 3D flow. Given this 3D flow, the dual-stream L-VO network can then predict the 6DOF relative pose and furthermore reconstruct the vehicle trajectory. In order to learn the correlation between motion directions, the Bivariate Gaussian modelling is employed in the loss function. The L-VO network achieves an overall performance of 2.68 rotational error on the KITTI odometry benchmark. Moreover, the learned depth is fully leveraged to generate a dense 3D map. As a result, an entire visual SLAM system, that is, learning monocular odometry combined with dense 3D mapping, is achieved.


page 1

page 3

page 6

page 8


Sparse2Dense: From direct sparse odometry to dense 3D reconstruction

In this paper, we proposed a new deep learning based dense monocular SLA...

DeepVO: A Deep Learning approach for Monocular Visual Odometry

Deep Learning based techniques have been adopted with precision to solve...

SD-6DoF-ICLK: Sparse and Deep Inverse Compositional Lucas-Kanade Algorithm on SE(3)

This paper introduces SD-6DoF-ICLK, a learning-based Inverse Composition...

Learning a Depth Covariance Function

We propose learning a depth covariance function with applications to geo...

Instant Visual Odometry Initialization for Mobile AR

Mobile AR applications benefit from fast initialization to display world...

Multi-Hypothesis Visual-Inertial Flow

Estimating the correspondences between pixels in sequences of images is ...

AD-VO: Scale-Resilient Visual Odometry Using Attentive Disparity Map

Visual odometry is an essential key for a localization module in SLAM sy...