Two Stream Networks for Self-Supervised Ego-Motion Estimation

10/04/2019
by   Rares Ambrus, et al.
0

Learning depth and camera ego-motion from raw unlabeled RGB video streams is seeing exciting progress through self-supervision from strong geometric cues. To leverage not only appearance but also scene geometry, we propose a novel self-supervised two-stream network using RGB and inferred depth information for accurate visual odometry. In addition, we introduce a sparsity-inducing data augmentation policy for ego-motion learning that effectively regularizes the pose network to enable stronger generalization performance. As a result, we show that our proposed two-stream pose network achieves state-of-the-art results among learning-based methods on the KITTI odometry benchmark, and is especially suited for self-supervision at scale. Our experiments on a large-scale urban driving dataset of 1 million frames indicate that the performance of our proposed architecture does indeed scale progressively with more data.

READ FULL TEXT
research
03/03/2022

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...
research
04/03/2020

Towards Better Generalization: Joint Depth-Pose Learning without PoseNet

In this work, we tackle the essential problem of scale inconsistency for...
research
08/15/2020

Neural Ray Surfaces for Self-Supervised Learning of Depth and Ego-motion

Self-supervised learning has emerged as a powerful tool for depth and eg...
research
02/14/2023

Event-guided Multi-patch Network with Self-supervision for Non-uniform Motion Deblurring

Contemporary deep learning multi-scale deblurring models suffer from man...
research
11/14/2022

AsyncNeRF: Learning Large-scale Radiance Fields from Asynchronous RGB-D Sequences with Time-Pose Function

Large-scale radiance fields are promising mapping tools for smart transp...
research
04/23/2018

VLocNet++: Deep Multitask Learning for Semantic Visual Localization and Odometry

Visual localization is one of the fundamental enablers of robot autonomy...
research
08/04/2021

Self-Supervised Learning of Depth and Ego-Motion from Video by Alternative Training and Geometric Constraints from 3D to 2D

Self-supervised learning of depth and ego-motion from unlabeled monocula...

Please sign up or login with your details

Forgot password? Click here to reset