FoundationVIO fuses IMU with foundation-model predictions to fix metric scale in feed-forward SLAM

zhenjun_zhao · x · 2026-10-17

• Problem: Feed-forward geometric foundation models (GFMs) predict dense geometry and camera poses from image batches, but only up-to-scale — no true metric scale, plaguing GFM-enabled SLAM with scale-ambiguous trajectories.
• Method: FoundationVIO integrates inertial sensing with GFM predictions in a factor graph containing IMU preintegration, GFM pose, and batch-to-batch scale consistency factors, jointly estimating per-batch scale plus per-frame pose, velocity, and biases.
• Results: On Aria Office, ScaRF-SLAM, and Oxford Spires datasets, odometry matches classical SOTA VIO (OKVIS2, ORB-SLAM3, VINS-Fusion) while dense reconstruction F-scores beat GFM-SLAM baselines like DA3-Streaming and VGGT(D)-SLAM; a minimal GFM loop-closure yields a full visual-inertial SLAM system.
• Practicality: Works with ubiquitous camera+IMU setups, runs near real-time on a consumer laptop GPU, code released.

Original post →

More from Embodied

• Contact-UAN: MIT's residual world model fixes humanoid sim-to-real with 6.5 minutes of data — kevin_zakka · 2026-10-17
• ROS 2 LiDAR localization runs 390 m outdoors on handheld Livox MID-360 — rsasaki0109 · 2026-10-17
• Embodied Astra tops RoboMME at 92.1% — beating humans by just keeping full visual history in context — hankyang94 · 2026-10-17
• ROS weekly: ROSCon China kicks off in Shanghai, ROS By-The-Bay set for Oct 22 at Intrinsic — kscottz · 2026-10-17
• Simulated robotics eval: Claude Opus 5.5 preferred over Opus 5 in 14 of 16 comparisons — qinzytech · 2026-10-17
• RootSLAM: square-root bundle adjustment makes visual-inertial SLAM up to 20x faster — zhenjun_zhao · 2026-10-17

Embodied channel →