The 2025 #TRO #BestPaper Award is FAST-LIVO2!
A direct LIDAR-inertial #VisualOdometry system that tightly fuses #LiDAR, IMU, & camera data for robust, real-time state estimation. Fast, accurate, and thoroughly validated across challenging environments.
https://ieeexplore.ieee.org/document/10757429
A direct LIDAR-inertial #VisualOdometry system that tightly fuses #LiDAR, IMU, & camera data for robust, real-time state estimation. Fast, accurate, and thoroughly validated across challenging environments.
https://ieeexplore.ieee.org/document/10757429
July 22, 2026 at 8:01 PM
The 2025 #TRO #BestPaper Award is FAST-LIVO2!
A direct LIDAR-inertial #VisualOdometry system that tightly fuses #LiDAR, IMU, & camera data for robust, real-time state estimation. Fast, accurate, and thoroughly validated across challenging environments.
https://ieeexplore.ieee.org/document/10757429
A direct LIDAR-inertial #VisualOdometry system that tightly fuses #LiDAR, IMU, & camera data for robust, real-time state estimation. Fast, accurate, and thoroughly validated across challenging environments.
https://ieeexplore.ieee.org/document/10757429
The Visual Odometry Transformer (VoT) estimates camera motion end‑to‑end from monocular images, eliminating feature matching, and runs over three times faster than pipelines. Read more: https://getnews.me/visual-odometry-transformer-enables-end-to-end-motion-estimation/ #visualodometry #robotics
October 7, 2025 at 12:28 PM
The Visual Odometry Transformer (VoT) estimates camera motion end‑to‑end from monocular images, eliminating feature matching, and runs over three times faster than pipelines. Read more: https://getnews.me/visual-odometry-transformer-enables-end-to-end-motion-estimation/ #visualodometry #robotics
A self‑supervised geometry‑guided init adds a frozen monocular depth prior to dense bundle adjustment, cutting translation error on KITTI odometry and improving DDAD results. https://getnews.me/self-supervised-geometry-guided-initialization-boosts-monocular-visual-odometry/ #visualodometry #ddad
October 1, 2025 at 7:55 AM
A self‑supervised geometry‑guided init adds a frozen monocular depth prior to dense bundle adjustment, cutting translation error on KITTI odometry and improving DDAD results. https://getnews.me/self-supervised-geometry-guided-initialization-boosts-monocular-visual-odometry/ #visualodometry #ddad
BEV-ODOM2 improves monocular visual odometry accuracy, achieving about 40% lower relative translation error on benchmarks such as KITTI, NCLT, Oxford RobotCar and ZJH-VO. https://getnews.me/bev-odom2-improves-monocular-visual-odometry-for-ground-robots/ #bevodom2 #visualodometry #robotics
September 19, 2025 at 9:26 PM
BEV-ODOM2 improves monocular visual odometry accuracy, achieving about 40% lower relative translation error on benchmarks such as KITTI, NCLT, Oxford RobotCar and ZJH-VO. https://getnews.me/bev-odom2-improves-monocular-visual-odometry-for-ground-robots/ #bevodom2 #visualodometry #robotics