SelfVIO: Self-Supervised Deep Monocular Visual-Inertial Odometry and Depth Estimation

by   Yasin Almalioglu, et al.

In the last decade, numerous supervised deep learning approaches requiring large amounts of labeled data have been proposed for visual-inertial odometry (VIO) and depth map estimation. To overcome the data limitation, self-supervised learning has emerged as a promising alternative, exploiting constraints such as geometric and photometric consistency in the scene. In this study, we introduce a novel self-supervised deep learning-based VIO and depth map recovery approach (SelfVIO) using adversarial training and self-adaptive visual-inertial sensor fusion. SelfVIO learns to jointly estimate 6 degrees-of-freedom (6-DoF) ego-motion and a depth map of the scene from unlabeled monocular RGB image sequences and inertial measurement unit (IMU) readings. The proposed approach is able to perform VIO without the need for IMU intrinsic parameters and/or the extrinsic calibration between the IMU and the camera. estimation and single-view depth recovery network. We provide comprehensive quantitative and qualitative evaluations of the proposed framework comparing its performance with state-of-the-art VIO, VO, and visual simultaneous localization and mapping (VSLAM) approaches on the KITTI, EuRoC and Cityscapes datasets. Detailed comparisons prove that SelfVIO outperforms state-of-the-art VIO approaches in terms of pose estimation and depth recovery, making it a promising approach among existing methods in the literature.


page 1

page 4

page 7


GANVO: Unsupervised Deep Monocular Visual Odometry and Depth Estimation with Generative Adversarial Networks

In the last decade, supervised deep learning approaches have been extens...

RIO: Rotation-equivariance supervised learning of robust inertial odometry

This paper introduces rotation-equivariance as a self-supervisor to trai...

DeepVIO: Self-supervised Deep Learning of Monocular Visual Inertial Odometry using 3D Geometric Constraints

This paper presents an self-supervised deep learning network for monocul...

Enhancing self-supervised monocular depth estimation with traditional visual odometry

Estimating depth from a single image represents an attractive alternativ...

Enhancing self-supervised monocular depth estimationwith traditional visual odometry

Estimating depth from a single image represents an attractive alternativ...

Robust Self-Supervised Extrinsic Self-Calibration

Autonomous vehicles and robots need to operate over a wide variety of sc...

Self-Supervised Ego-Motion Estimation Based on Multi-Layer Fusion of RGB and Inferred Depth

In existing self-supervised depth and ego-motion estimation methods, ego...

Please sign up or login with your details

Forgot password? Click here to reset