← Search

Markus Schön

1 accepted papers

2021

MGNet: Monocular Geometric Scene Understanding for Autonomous Driving

ICCV 2021poster

We introduce MGNet, a multi-task framework for monocular geometric scene understanding. We define monocular geometric scene understanding as the combination of two known tasks: Panoptic segmentation and self-supervised monocular depth estimation. Panoptic segmentation captures the full scene not onl…

Cited by 51PDFcodeScholar