Research Project: Video Understanding for Autonomous Driving
Loading...
Contributors
Funders
ID
EC.00130
Authors
Güney, Fatma
Faculty Member
Publications
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.
