NAVER LABS has made available five new indoor datasets for large scale visual localization in crowded public spaces.
Releasing first of a kind large-scale localization datasets in crowded indoor spaces
at
| Donghwan Lee, Soohyun Ryu, Suyong Yeon, Yonghan Lee, Deokhwa Kim, Cheolho Han, Yohann Cabon, Philippe Weinzaepfel, Nicolas Guerin, Gabriela Csurka Khedari, Martin Humenberger |
| 2021 |
The datasets, which have over 130,000 images, cover several floors of a large department store with shops and restaurants, a busy metro station, underground train platforms and an underground shopping mall providing an immensely rich combination of static scenes and moving objects. The datasets are first of a kind because the images are captured in large scale public spaces and in realistic conditions. They are being made available to help researchers and developers increase the applicability of visual localization algorithms in real-world applications such as AR, autonomous driving and robotics. The datasets are available at naverlabs.com/datasets and in the kapture dataset downloader.
Visual localization algorithms estimate the camera pose of a given image which is an important task in robotics, autonomous driving and in augmented reality (AR) and the results of modern visual localization methods have been promising enough for some real-world applications to have been developed such as AR navigation.
Challenges. Indoor environments differ from outdoor scenes in a number of important aspects concerning visual localization. For example, although lighting conditions in indoor spaces tend to be more constant than those in the outside world, indoor spaces are typically narrower so small camera movements can cause large changes in viewpoint. Dynamic objects like people, trolleys, TV screens, areas with no texture and repetitive patterns are also challenging for visual localization and there are many more of these in indoor spaces.
Existing datasets. In outdoor environments, the structure-from-motion (SfM) technique is effective in generating ground truth camera poses, which are necessary for all localization algorithms. Unfortunately, due to the aforementioned challenges, large-scale SfM is more difficult and often impossible to apply to indoor spaces. As a consequence, the area covered by existing indoor datasets (Stanford, ScanNet, Matterport 3D, 7 scenes, InLoc and Baidu) is only sparsely sampled by the provided images (e.g. only one image every 2 meters).
Furthermore, while the presence of people is an important aspect for a realistic dataset, privacy issues and limitations of data acquisition (standard SfM often fails) typically hinder the inclusion of crowds in state-of-the-art datasets.
NAVER LABS datasets. To contribute to the need for more training data, and in particular data of indoor environments, NAVER LABS has made available five new localization datasets acquired in challenging real-world indoor environments. The datasets were captured in a large shopping mall and a busy metro station in Seoul, South Korea and include images and depth maps obtained from a dedicated mapping platform with ten cameras and two 3D laser scanners. Compared to existing indoor datasets, the proposed datasets provide dense image sampling and cover many challenges of indoor visual localization as shown in Figure 1. In addition, the datasets consist of captures of sequences with time intervals of up to 128 days providing changes over time. To address the problem that SfM cannot be used alone to estimate precise ground truth camera poses for large indoor spaces, we developed a novel, automated pipeline that utilizes both LiDAR SLAM and SfM algorithms. The proposed pipeline applies LiDAR-based pose-graph SLAM to estimate the trajectories of our dedicated mapping platform M1X. For full details on the datasets see our CVPR 2021 paper (4) and/or article Indoor Localization Dataset V1.0 (Dept. & Metro St.)
Kapture. The datasets are provided in the unified data format kapture. Kapture is being increasingly adopted as the toolbox that accompanies it makes the execution of modern visual localization methods easy and the conversion into other formats such as OpenMVG and COLMAP simple.
(1) Dataset: https://www.naverlabs.com/en/datasets
(2) kapture data format: https://github.com/naver/kapture
(3) kapture toolbox (visual localization): https://github.com/naver/kapture-localization
(4) Large-scale localization datasets in crowded indoor spaces, Donghwan Lee, Soohyun Ryu, Suyong Yeon, Yonghan Lee, Deokhwa Kim, Cheolho Han, Yohann Cabon, Philippe Weinzaepfel, Nicolas Guerin, Gabriela Csurka, and Martin Humenberger, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021. [arXiV 2105.08941]