Kornia releases open-source Rust visual-inertial SLAM pipeline kornia-slam v0.1
edgarriba · x · 2026-10-16
Kornia has open-sourced kornia-slam v0.1, a visual-inertial SLAM and VIO pipeline written in Rust, and is looking for early testers and contributors.
Key capabilities:
- Tracks the camera via ORB features with monocular, stereo, or stereo+IMU setups
- Refines the map with local bundle adjustment and visual-inertial BA when an IMU is present
- Loop closure via DBoW2 place recognition plus pose-graph optimisation to correct drift
- Reads EuRoC/Hilti datasets, MCAP recordings, and live OAK-D/UVC cameras
- Visualises via terminal UI or Rerun, scores runs against ground truth with ATE/RPE
It can also plug into the Copper deterministic robotics runtime via cu-kornia-vio, and the README includes full cargo quick-start commands.
Related event: Kornia Open-Sources Rust-Based Visual-Inertial SLAM Pipeline kornia-slam(2 posts)→
More from Research
- A beginner-friendly introduction to causal inference kicks off, Part 1 — Nasereliver · 2026-10-16
- FBI method trains for Pass@K with one sample per update at 12.3% of the cost — EmtiyazKhan · 2026-10-16
- Berkeley researchers sample humanoid robot policies directly from weight space with diffusion — berkeley_ai · 2026-10-16
- OneWM: unified causal training shows world and action modeling improve each other — IAAI233 · 2026-10-16
- Baidu's Virtual Head Attention tames the KV cache, FLOPs, quality triangle in long-context LLMs — baidu · 2026-10-16
- 5.8M-param Speech Event Detector adds laughs, breaths and背景 sounds to Whisper transcripts — Ayush Kumar Bar · 2026-10-16