From 2D to 3D: AISG-SLA Visual Localization Challenge

TL;DR

This paper presents the organization of the AISG-SLA Visual Localization Challenge at IJCAI 2023, which aimed to advance monocular camera pose estimation from 2D images in 3D space, attracting over 300 participants and providing a new dataset.

Contribution

The paper introduces a large-scale visual localization challenge and dataset to promote research in monocular pose estimation from 2D images in 3D environments.

Findings

High accuracy achieved by winning teams in pose estimation

The challenge attracted over 300 participants worldwide

The dataset is available for further research

Abstract

Research in 3D mapping is crucial for smart city applications, yet the cost of acquiring 3D data often hinders progress. Visual localization, particularly monocular camera position estimation, offers a solution by determining the camera's pose solely through visual cues. However, this task is challenging due to limited data from a single camera. To tackle these challenges, we organized the AISG-SLA Visual Localization Challenge (VLC) at IJCAI 2023 to explore how AI can accurately extract camera pose data from 2D images in 3D space. The challenge attracted over 300 participants worldwide, forming 50+ teams. Winning teams achieved high accuracy in pose estimation using images from a car-mounted camera with low frame rates. The VLC dataset is available for research purposes upon request via vlc-dataset@aisingapore.org.