Semantics-Driven Unsupervised Learning for Monocular Depth and Ego-Motion Estimation

06/08/2020
by   Xiaobin Wei, et al.
0

We propose a semantics-driven unsupervised learning approach for monocular depth and ego-motion estimation from videos in this paper. Recent unsupervised learning methods employ photometric errors between synthetic view and actual image as a supervision signal for training. In our method, we exploit semantic segmentation information to mitigate the effects of dynamic objects and occlusions in the scene, and to improve depth prediction performance by considering the correlation between depth and semantics. To avoid costly labeling process, we use noisy semantic segmentation results obtained by a pre-trained semantic segmentation network. In addition, we minimize the position error between the corresponding points of adjacent frames to utilize 3D spatial information. Experimental results on the KITTI dataset show that our method achieves good performance in both depth and ego-motion estimation tasks.

READ FULL TEXT

page 3

page 6

page 12

page 14

research
04/01/2021

Unsupervised Learning of Monocular Depth and Ego-Motion Using Multiple Masks

A new unsupervised learning method of depth and ego-motion using multipl...
research
03/03/2020

DiPE: Deeper into Photometric Errors for Unsupervised Learning of Depth and Ego-motion from Monocular Videos

Unsupervised learning of depth and ego-motion from unlabelled monocular ...
research
04/11/2020

Improving Semantic Segmentation through Spatio-Temporal Consistency Learned from Videos

We leverage unsupervised learning of depth, egomotion, and camera intrin...
research
06/12/2019

Unsupervised Monocular Depth and Ego-motion Learning with Structure and Semantics

We present an approach which takes advantage of both structure and seman...
research
06/04/2020

Unsupervised Depth Learning in Challenging Indoor Video: Weak Rectification to Rescue

Single-view depth estimation using CNNs trained from unlabelled videos h...
research
03/08/2023

RM-Depth: Unsupervised Learning of Recurrent Monocular Depth in Dynamic Scenes

Unsupervised methods have showed promising results on monocular depth es...
research
12/12/2013

Unsupervised learning of depth and motion

We present a model for the joint estimation of disparity and motion. The...

Please sign up or login with your details

Forgot password? Click here to reset