Research Project:
Video Understanding for Autonomous Driving

Loading...
Project Logo

Contributors

Funders

ID

EC.00130

Authors

Person
Güney, Fatma
Faculty Member

Publications

Thumbnail Image
PublicationOpen Access
Self-supervised monocular scene decomposition and depth estimation
(IEEE Computer Society, 2021) Güney, Fatma; Safadoust, Sadra; Department of Computer Engineering; Graduate School of Sciences and Engineering; KUIS AI (Koç University & İş Bank Artificial Intelligence Center); Yes; College of Engineering; GRADUATE SCHOOL OF SCIENCES AND ENGINEERING; Research Center
Self-supervised monocular depth estimation approaches either ignore independently moving objects in the scene or need a separate segmentation step to identify them. We propose MonoDepthSeg to jointly estimate depth and segment moving objects from monocular video without using any ground-truth labels. We decompose the scene into a fixed number of components where each component corresponds to a region on the image with its own transformation matrix representing its motion. We estimate both the mask and the motion of each component efficiently with a shared encoder. We evaluate our method on three driving datasets and show that our model clearly improves depth estimation while decomposing the scene into separately moving components.

Organizational Units

Description

Keywords