Professor Daniel Cremers, Artisense founder and CSO, co-authored a paper and its demo video won the Best Demo Award at an international conference

News Release

December 28th, 2021
Kudan Inc.


Professor Daniel Cremers, Artisense founder and CSO, co-authored a paper on
accurate tracking and 3D map construction using a monocular camera, and its
related demo video won the Best Demo Award at an international conference


Kudan Inc. (headquarters in Shibuya-ku; CEO Daiu Ko; hereafter “Kudan”), a leading
provider of simultaneous localization and mapping (SLAM) solutions across multiple
industries and applications, is pleased to announce that Professor Daniel Cremers, a founder
and CSO (Chief Scientific Officer) of Artisense GmbH (hereafter “Artisense”), a Kudan group
company, as well as the Head of the Chair for Computer Vision and Artificial Intelligence at
the Technical University of Munich (TUM), co-authored a paper entitled "TANDEM:
Tracking and Dense Mapping in Real-time using Deep Multi-view Stereo”, which was
presented at the Conference on Robot Learning (CoRL2021).
We are also excited to announce that the demo video won the Best Demo Award at the
International Conference on 3D Vision 2021 (3DV2021), where research results covering a
broad variety of topics in the area of 3D research in computer vision and graphics are
disseminated.


Paper outline:
https://vision.in.tum.de/research/vslam/tandem


Check below for the paper:
https://openreview.net/pdf?id=FzMHiDesj0I


Demo video:
https://www.youtube.com/watch?v=L4C8Q6Gvl1w


List of Award Winners:
https://3dv2021.surrey.ac.uk/prizes/


In their paper, Prof. Cremers et al. present the results of their research on a method called
TANDEM for highly accurate tracking and 3D environment reconstruction using deep
learning with a monocular camera. TANDEM outperforms other conventional and deep
learning-based monocular visual odometry (VO) tracking methods, and has also proven its
performance in reconstructing robust and highly accurate 3D maps.



News Release
Artisense continues to promote research and development of cutting-edge technologies
backed by academic research, led by Prof. Cremers. Also, Kudan group as a whole, as leading
companies in the computer vision industry, will strive to continuously establish competitive
advantages in SLAM technology on a global scale and accelerate social implementation.


About Artisense Corporation
Artisense is a computer vision and sensor fusion software company that develops an
integrated positioning platform using cameras as a lead sensor for the automation of robots,
vehicles, and spatial intelligence applications. On a mission to accelerate the adoption of
autonomous robots and machines, Artisense provides products and technology for highly
accurate, robust, safe, and low-cost navigation in any space.
For more information, please refer to Artisense’s website at http://www.artisense.ai/.


About Kudan Inc.
Kudan (Tokyo Stock Exchange securities code: 4425) is a deep tech research and development
company specializing in algorithms for artificial perception (AP). As a complement to
artificial intelligence (AI), AP functions allow machines to develop autonomy. Currently,
Kudan is using its high-level technical innovation to explore business areas based on its own
milestone models established for deep tech which provide wide-ranging impact on several
major industrial fields.
For more information, please refer to Kudan’s website at https://www.kudan.io/.


■Company Details
Name: Kudan Inc.
Securities Code: 4425
Representative: CEO Daiu Ko


■For more details, please contact us from here.





3961