Sign in

Hide Matsuki

@hidematsu82.bsky.social
18 followers 38 following 0 posts

PhD candidate at the Dyson Robotics Lab, Imperial College London (SLAM, Dynamic Vision, Robotics). Love to make something fast, intuitive, and interactive. muskie82.github.io

PostsRepliesMedia
Reposted by Hide Matsuki
Vision and Graphics Trends @si-cv-graphics.bsky.social · 18/12/2025
𝗨𝗻𝗶𝗳𝗶𝗲𝗱 𝗦𝗲𝗺𝗮𝗻𝘁𝗶𝗰 𝗧𝗿𝗮𝗻𝘀𝗳𝗼𝗿𝗺𝗲𝗿 𝗳𝗼𝗿 𝟯𝗗 𝗦𝗰𝗲𝗻𝗲 𝗨𝗻𝗱𝗲𝗿𝘀𝘁𝗮𝗻𝗱𝗶𝗻𝗴 Sebastian Koch, Johanna Wald, Hide Matsuki ... Federico Tombari arxiv.org/abs/2512.14364 Trending on www.scholar-inbox.com
063
Reposted by Hide Matsuki
Andrew Davison @ajdavison.bsky.social · 16/05/2025
Full draft of the SLAM Handbook now released --- available as a free PDF, with a printed version coming soon. Now including Part 3, "From SLAM to Spatial AI" (I knew it would catch on eventually), with contributions from @hidematsu82.bsky.social and me. #SpatialAI github.com/SLAM-Handboo...
github.com
GitHub - SLAM-Handbook-contributors/slam-handbook-public-release: Release repo for our SLAM Handbook
Release repo for our SLAM Handbook. Contribute to SLAM-Handbook-contributors/slam-handbook-public-release development by creating an account on GitHub.
1225
Reposted by Hide Matsuki
Riku Murai @rmurai0610.bsky.social · 16/12/2024
For more please visit: Website: edexheim.github.io/mast3r-slam/ Video: youtu.be/wozt71NBFTQ
youtu.be
MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priors
YouTube video by Riku Murai
091
Reposted by Hide Matsuki
Riku Murai @rmurai0610.bsky.social · 16/12/2024
For robustness, MASt3R-SLAM performs relocalisation allowing it to handle the kidnapped robot problem. As a purely monocular SLAM, it loses track when the camera’s view is obstructed, but as soon as the view is unblocked, it immediately relocalises and resumes mapping.
1122
Reposted by Hide Matsuki
Riku Murai @rmurai0610.bsky.social · 16/12/2024
Introducing MASt3R-SLAM, the first real-time monocular dense SLAM with MASt3R as a foundation. Easy to use like DUSt3R/MASt3R, from an uncalibrated RGB video it recovers accurate, globally consistent poses & a dense map. With @ericdexheimer.bsky.social* @ajdavison.bsky.social (*Equal Contribution)
510016
Reposted by Hide Matsuki
Andrew Davison @ajdavison.bsky.social · 16/12/2024
MASt3R-SLAM: easily the most robust dense monocular SLAM system I've ever seen, and also very accurate. Real-time, RGB only (no IMU), handles unknown focal length and zoom. More new videos coming soon @ericdexheimer.bsky.social @rmurai0610.bsky.social. Paper and more: edexheim.github.io/mast3r-slam
edexheim.github.io
MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priors
MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priors
0406
Reposted by Hide Matsuki
Noah Snavely @snavely.bsky.social · 27/11/2024
Nice question! My favorite scene representation is code -- procedurally generated scenes. One of my most beloved videos is Inigo Quilez's "Painting a Landscape with Maths" (www.youtube.com/watch?v=BFld...). This nicely shows the power of composing simple functions in synthesizing visual complexity.
youtube.com
Painting a Landscape with Maths
YouTube video by Inigo Quilez
2182