Unsupervised Monocular Depth Prediction for Indoor Continuous Video Streams

11/20/2019
by   Yinglong Feng, et al.
20

This paper studies unsupervised monocular depth prediction problem. Most of existing unsupervised depth prediction algorithms are developed for outdoor scenarios, while the depth prediction work in the indoor environment is still very scarce to our knowledge. Therefore, this work focuses on narrowing the gap by firstly evaluating existing approaches in the indoor environments and then improving the state-of-the-art design of architecture. Unlike typical outdoor training dataset, such as KITTI with motion constraints, data for indoor environment contains more arbitrary camera movement and short baseline between two consecutive images, which deteriorates the network training for the pose estimation. To address this issue, we propose two methods: Firstly, we propose a novel reconstruction loss function to constraint pose estimation, resulting in accuracy improvement of the predicted disparity map; secondly, we use an ensemble learning with a flipping strategy along with a median filter, directly taking operation on the output disparity map. We evaluate our approaches on the TUM RGB-D and self-collected datasets. The results have shown that both approaches outperform the previous state-of-the-art unsupervised learning approaches.

READ FULL TEXT

page 4

page 5

page 6

page 7

page 8

research
07/18/2022

MonoIndoor++:Towards Better Practice of Self-Supervised Monocular Depth Estimation for Indoor Environments

Self-supervised monocular depth estimation has seen significant progress...
research
11/19/2018

Indoor GeoNet: Weakly Supervised Hybrid Learning for Depth and Pose Estimation

Humans naturally perceive a 3D scene in front of them through accumulati...
research
01/17/2020

Unsupervised Learning of Camera Pose with Compositional Re-estimation

We consider the problem of unsupervised camera pose estimation. Given an...
research
07/28/2021

Learning-Based Depth and Pose Estimation for Monocular Endoscope with Loss Generalization

Gastroendoscopy has been a clinical standard for diagnosing and treating...
research
03/14/2022

RAUM-VO: Rotational Adjusted Unsupervised Monocular Visual Odometry

Unsupervised learning for monocular camera motion and 3D scene understan...
research
08/27/2018

A Deeper Insight into the UnDEMoN: Unsupervised Deep Network for Depth and Ego-Motion Estimation

This paper presents an unsupervised deep learning framework called UnDEM...
research
10/20/2019

Moving Indoor: Unsupervised Video Depth Learning in Challenging Environments

Recently unsupervised learning of depth from videos has made remarkable ...

Please sign up or login with your details

Forgot password? Click here to reset