Log In Sign Up

Unsupervised Monocular Depth Learning with Integrated Intrinsics and Spatio-Temporal Constraints

by   Kenny Chen, et al.

Monocular depth inference has gained tremendous attention from researchers in recent years and remains as a promising replacement for expensive time-of-flight sensors, but issues with scale acquisition and implementation overhead still plague these systems. To this end, this work presents an unsupervised learning framework that is able to predict at-scale depth maps and egomotion, in addition to camera intrinsics, from a sequence of monocular images via a single network. Our method incorporates both spatial and temporal geometric constraints to resolve depth and pose scale factors, which are enforced within the supervisory reconstruction loss functions at training time. Only unlabeled stereo sequences are required for training the weights of our single-network architecture, which reduces overall implementation overhead as compared to previous methods. Our results demonstrate strong performance when compared to the current state-of-the-art on multiple sequences of the KITTI driving dataset.


page 1

page 2

page 3

page 5


UnDeepVO: Monocular Visual Odometry through Unsupervised Deep Learning

We propose a novel monocular visual odometry (VO) system called UnDeepVO...

Unsupervised Simultaneous Learning for Camera Re-Localization and Depth Estimation from Video

We present an unsupervised simultaneous learning framework for the task ...

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...

Full Surround Monodepth from Multiple Cameras

Self-supervised monocular depth and ego-motion estimation is a promising...

Unsupervised Learning of Monocular Depth Estimation with Bundle Adjustment, Super-Resolution and Clip Loss

We present a novel unsupervised learning framework for single view depth...

Unsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Video

Recent work has shown that CNN-based depth and ego-motion estimators can...

Improved Point Transformation Methods For Self-Supervised Depth Prediction

Given stereo or egomotion image pairs, a popular and successful method f...