DefVINS: Visual-Inertial Odometry for Deformable Scenes
This addresses a specific challenge in robotics and AR/VR for navigating non-rigid environments, representing an incremental improvement over existing VIO methods.
The paper tackles the problem of visual-inertial odometry failing in deformable scenes by introducing DefVINS, which separates rigid and non-rigid motion using an embedded deformation graph, resulting in improved robustness as shown in ablation studies.
Deformable scenes violate the rigidity assumptions underpinning classical visual-inertial odometry (VIO), often leading to over-fitting to local non-rigid motion or severe drift when deformation dominates visual parallax. We introduce DefVINS, a visual-inertial odometry framework that explicitly separates a rigid, IMU-anchored state from a non--rigid warp represented by an embedded deformation graph. The system is initialized using a standard VIO procedure that fixes gravity, velocity, and IMU biases, after which non-rigid degrees of freedom are activated progressively as the estimation becomes well conditioned. An observability analysis is included to characterize how inertial measurements constrain the rigid motion and render otherwise unobservable modes identifiable in the presence of deformation. This analysis motivates the use of IMU anchoring and informs a conditioning-based activation strategy that prevents ill-posed updates under poor excitation. Ablation studies demonstrate the benefits of combining inertial constraints with observability-aware deformation activation, resulting in improved robustness under non-rigid environments.