Privacy Preserving Visual SLAM

no code implementations • ECCV 2020 • Mikiya Shibuya, Shinya Sumikura, Ken Sakurada

This study proposes a privacy-preserving Visual SLAM framework for estimating camera poses and performing bundle adjustment with mixed line and point clouds in real time.

Computational Efficiency Privacy Preserving

OpenVSLAM: A Versatile Visual SLAM Framework

4 code implementations • 2 Oct 2019 • Shinya Sumikura, Mikiya Shibuya, Ken Sakurada

In this paper, we introduce OpenVSLAM, a visual SLAM framework with high usability and extensibility.

Weakly Supervised Silhouette-based Semantic Scene Change Detection

1 code implementation • 29 Nov 2018 • Ken Sakurada, Mikiya Shibuya, Weimin WANG

A straightforward approach for this task is to train a semantic change detection network directly from a large-scale dataset in an end-to-end manner.

Change Detection Scene Change Detection