Monocular SLAM Under Corruption: Learned Trackers Trade Catastrophic Failure for Drift
zhenjun_zhao · x · 2026-09-01
Paper: Failure or Drift? Evaluating Monocular SLAM under Synthetic and Real-World Corruptions (3rd NeuSLAM workshop, ECCV 2026).
- Evaluates classical ORB-SLAM2 and learned trackers DPVO and DROID-SLAM under image-space, geometry-aware, and compound corruptions, compared with real adverse conditions from 4Seasons.
- Rather than reducing robustness to a single trajectory error, the evaluation separates explicit tracking failure from drift accumulated by methods that remain active.
- Findings: learned trackers largely replace catastrophic loss with sustained, sometimes severe drift; the apparent ordering of learned systems changes with the physical fidelity of the corruption — structured rain/fog proxies preserve real-world ordering, a simple illumination proxy does not. Code is released.
More from Embodied
- Tesla FSD slashes emergency braking by up to 84% vs human drivers — XFreeze · 2026-09-01
- NVIDIA Introduces Hydra-0: A Generalist World Model for Robotics — chris_j_paxton · 2026-09-01
- Galbot ET1 humanoid robot masters autonomous tennis play — Olivier__OG · 2026-09-01
- AInnoGC Updates and Profitability as Industrial Agents Deploy — 智东西 · 2026-09-01
- Mech-Mind IPOs with 'Eye-Brain-Hand' Focus — 智东西 · 2026-09-01
- Using an iPhone 13 mini as a Reinforcement Learning Environment — willcb · 2026-09-01