VIGS-SLAM: visual-inertial 3D Gaussian Splatting SLAM hits SOTA on five datasets
rsasaki0109 · x · 2026-09-10
VIGS-SLAM (ECCV 2026, from ETH Zurich's cvg group with Marc Pollefeys) is a tightly coupled visual-inertial 3D Gaussian Splatting SLAM system that takes RGB frames plus IMU readings, tracks the camera trajectory robustly in real time, and reconstructs high-fidelity Gaussian maps, achieving state-of-the-art results across five challenging datasets. Code is open-sourced on GitHub with an iPhone capture pipeline, real-time demo, Docker setup, and pretrained models.
More from Embodied
- Unitree G1 Bluetooth bug grants root: what a microkernel RTOS would and wouldn't have prevented — pdamodaran · 2026-09-10
- Huawei's new tri-fold panned: cheap colors and a bulky camera island — Linahuaa · 2026-09-10
- Humanoid actuator startup claims $160M order and 300 sets/month — met with skepticism — yongqianme · 2026-09-10
- Duo device leases for $58/month, or 'two dollars a day' — asymco · 2026-09-10
- SF apartment cleaned by a humanoid robot at $30/hour, powered by Qwen 3.5 — Aizkmusic · 2026-09-10
- First US rare earth magnet plant in 40 years breaks ground, 7,000 tons/year — MatthewChang · 2026-09-10