Inertial Guided Uncertainty Estimation of Feature Correspondence in Visual-Inertial Odometry/SLAM

no code implementations • 7 Nov 2023 • Seongwook Yoon, Jaehyun Kim, Sanghoon Sull

Visual odometry and Simultaneous Localization And Mapping (SLAM) has been studied as one of the most important tasks in the areas of computer vision and robotics, to contribute to autonomous navigation and augmented reality systems.

Autonomous Navigation Simultaneous Localization and Mapping +1

Vision System of Curling Robots: Thrower and Skip

no code implementations • 20 Apr 2022 • Seongwook Yoon, Gayoung Kim, Myungpyo Hong, Sanghoon Sull

Our vision system in the skip robot recognize every stones on the curling sheet precisely.

Controllable Missingness from Uncontrollable Missingness: Joint Learning Measurement Policy and Imputation

no code implementations • 8 Apr 2022 • Seongwook Yoon, Jaehyun Kim, Heejeong Lim, Sanghoon Sull

The main idea is that 1) the data generation method is inherited by imputation method, and 2) the adaptation of imputation encourages measurement policy to learn more than individual learning.

Imputation

GAMIN: Generative Adversarial Multiple Imputation Network for Highly Missing Data

no code implementations • CVPR 2020 • Seongwook Yoon, Sanghoon Sull

We synthesized highly missing datasets using MNIST and CelebA to perform various experiments.

Generative Adversarial Network Imputation