Hide Matsuki

I am a Research Engineer at Google within the GenXR team, part of Android XR. Our team conducts applied research on 3D GenAI and neural scene representations, led by Federico Tombari. .

I completed my PhD at the Dyson Robotics Lab, Imperial College London, supervised by Prof. Andrew Davison. During my doctoral studies, I was a research intern at Google Zurich, hosted by Federico Tombari and Keisuke Tateno.

Previously, I completed my Master's degree at the University of Tokyo. During my master's program, I had the opportunity to work at the Technische Universität München (TUM) with Prof. Daniel Cremers.

Between my master's and PhD degree, I worked as a computer vision engineer at Artisense, a startup co-founded by Prof. Cremers.

Email  /  Scholar  /  Twitter  /  Github

profile photo

Research

My Ph.D. research focused on real-time computer vision and robotics, with a particular emphasis on visual SLAM. I am currently interested in sequential models for video input that enable scalable learning for embodied agents. Our team periodically hires interns and student researchers; please contact me if you are interested in working at Google’s Munich or Zurich offices.

Publications
Image Unified Semantic Transformer for 3D Scene Understanding
Sebastian Koch, Johanna Wald, Hidenobu Matsuki, Pedro Hermosilla, Timo Ropinski, Federico Tombari
Arxiv, 2025
project page / paper

A single feed-forward model that unifies multiple 3D semantic tasks from RGB input.

Image 4DTAM: Non-Rigid Tracking and Mapping via Dynamic Surface Gaussians
Hidenobu Matsuki, Gwangbin Bae, Andrew J. Davison
IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR), 2025
project page / video / paper

4D scene reconstruction and camera ego-motion estimation framework based on dynamic surface gaussians.

Image Gaussian Splatting SLAM
Hidenobu Matsuki*, Riku Murai*, Paul H.J. Kelly, Andrew J. Davison
IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR), 2024   (Highlight, Best Demo Award)
project page / video / paper

The first Monocular SLAM using Gaussian Splatting as a master representation. The method also supports RGB-D mode.

PontTuset NEWTON: Neural View-Centric Mapping for On-the-Fly Large-Scale SLAM
Hidenobu Matsuki, Keisuke Tateno, Michael Niemeyer, Federico Tombari,
IEEE Robotics and Automation Letters (RA-L), 2024
paper

Multiple local Neural Fields for efficiently handling loop closure in large-scale SLAM.

PontTuset iMODE:Real-Time Incremental Monocular Dense Mapping Using Neural Field
Hidenobu Matsuki, Edgar Sucar, Tristan Laidlow, Kentaro Wada, Raluca Scona, Andrew J. Davison
IEEE International Conference on Robotics and Automation (ICRA), 2023   (Oral Presentation, Best Navigation Paper Award Finalist)
paper

Generic real-time monocular dense mapping pipeline utilizing the smoothness prior inhereint in Multi Layer Perceptron.

PontTuset CodeMapping: Real-Time Dense Mapping for Sparse SLAM using Compact Scene Representations
Hidenobu Matsuki, Raluca Scona, Jan Czarnowski, Andrew J. Davison,
IEEE Robotics and Automation Letters (RA-L), 2021
paper / video

Real-time dense mapping framework with compact scene representations from generataive model.

PontTuset Omnirectional DSO: Direct Sparse Odometry with Fisheye Cameras
Hidenobu Matsuki, Lukas von Stumberg, Vladyslav Usenko, Jörg Stückler, Daniel Cremers
IEEE Robotics and Automation Letters (RA-L), 2018
paper / video

Real-time direct visual odometry for omnidirectional cameras

Books
SLAM Handbook cover SLAM Handbook: From Localization and Mapping to Spatial Intelligence
Luca Carlone, Ayoung Kim, Frank Dellaert, Timothy Barfoot, Daniel Cremers
Cambridge University Press, 2025
Book link

I co-authored Chapter 14, “Map Representations with Differentiable Volume Rendering,” with Andy.

コンピュータビジョン最前線 Summer 2025 コンピュータビジョン最前線 Summer 2025 (in Japanese)
井尻 善久 編・牛久 祥孝 編・片岡 裕雄 編・藤吉 弘亘 編・延原 章平 編
共立出版 2025
Book link

I co-authored the chapter on 3D Gaussian Splatting with Keisuke Tateno.

Talks
  • CVIM研究会, Fukuoka, Japan (January 2025) — Presentation of the Japanese book chapter.
  • World Labs, San Francisco, USA (June 2024) — “Differentiable Rendering for Dense Visual SLAM.”

Academic Service
  • Conference Reviewer: NeurIPS, ICLR, ICML, ICRA, IROS
  • Journal Reviewer: T-PAMI, IJCV, T-RO, IJRR, RA-L, ISPRS

Misc
I am a big fan of Rugby, both for playing and watching. I played in an international match when I was in junior high school, and later competed in the Rugby Bundesliga while living in Germany (although it is a much smaller league than its soccer counterpart). I also enjoy drinking beer and whisky, traveling, and watching anime.

Thanks.