In this paper, we present a novel architecture and training methodology for learning monocular depth prediction, camera pose estimation, optical flow, and moving object segmentation using a common encoder in an unsupervised fashion. We demonstrate that the geometrical relationships between these tasks not only support joint unsupervised learning as shown in previous works but also allow them to share common features. We also show the advantage of using a two-stage learning approach to improve the performance of the base network.
Unsupervised Joint Multi-Task Learning of Vision Geometry Tasks
2021-07-11
1568700 byte
Conference paper
Electronic Resource
English
Multi-task Learning of Semantics,Geometry and Motion for Vision-based End-to-End Self-Driving
British Library Conference Proceedings | 2021
|Multi-task Learning of Semantics, Geometry and Motion for Vision-based End-to-End Self-Driving
SAE Technical Papers | 2021
|