Exploiting Geometric Structure in Monocular Video Frames for Self-Supervised Depth Estimation

Home

Discover

Bookmarks

Keep Up With Latest Trending Papers. Computer Science, AI and Machine Learning and more.Subscribe

CC BY

Source arXiv

Computer Vision

Exploiting Geometric Structure in Monocular Video Frames for Self-Supervised Depth Estimation

$S^3$Net: Semantic-Aware Self-supervised Depth Estimation with Monocular Videos and Synthetic Data

Depth estimation with monocular cameras enables the possibility of widespread use of cameras as low-cost depth estimation sensors in applications such as autonomous driving and robotics.

However, learning such a scalable depth estimation model would require a lot of labeled data which is expensive to collect.

We present a self-supervised framework which combines these complementary features : we use synthetic and real-world images for training while exploiting geometric, temporal, as well as semantic constraints across space and time in monocular video frames.

We present a unique way to train this self-supervised framework, and achieve (i) more than improvement over previous synthetic supervised approaches that use domain adaptation and (ii) more than improvement over previous self-supervised approaches which exploit geometric constraints from the real data.

Our novel consolidated architecture provides a new state-of-the-art in self-supervised depth estimation using monocular videos.

Authors

Bin Cheng, Inderjot Singh Saggu, Raunak Shah, Gaurav Bansal, Dinesh Bharadia

◐ Recommended Follows

◐ Latest Activity