EMoTive: Event-guided Trajectory Modeling for 3D Motion Estimation
By: Zengyu Wan , Wei Zhai , Yang Cao and more
Potential Business Impact:
Helps cameras see moving objects in 3D.
Visual 3D motion estimation aims to infer the motion of 2D pixels in 3D space based on visual cues. The key challenge arises from depth variation induced spatio-temporal motion inconsistencies, disrupting the assumptions of local spatial or temporal motion smoothness in previous motion estimation frameworks. In contrast, event cameras offer new possibilities for 3D motion estimation through continuous adaptive pixel-level responses to scene changes. This paper presents EMoTive, a novel event-based framework that models spatio-temporal trajectories via event-guided non-uniform parametric curves, effectively characterizing locally heterogeneous spatio-temporal motion. Specifically, we first introduce Event Kymograph - an event projection method that leverages a continuous temporal projection kernel and decouples spatial observations to encode fine-grained temporal evolution explicitly. For motion representation, we introduce a density-aware adaptation mechanism to fuse spatial and temporal features under event guidance, coupled with a non-uniform rational curve parameterization framework to adaptively model heterogeneous trajectories. The final 3D motion estimation is achieved through multi-temporal sampling of parametric trajectories, yielding optical flow and depth motion fields. To facilitate evaluation, we introduce CarlaEvent3D, a multi-dynamic synthetic dataset for comprehensive validation. Extensive experiments on both this dataset and a real-world benchmark demonstrate the effectiveness of the proposed method.
Similar Papers
E-MoFlow: Learning Egomotion and Optical Flow from Event Data via Implicit Regularization
CV and Pattern Recognition
Helps cameras understand movement without seeing everything.
EVLoc: Event-based Visual Localization in LiDAR Maps via Event-Depth Registration
CV and Pattern Recognition
Helps robots see and move in tricky places.
Event-based multi-view photogrammetry for high-dynamic, high-velocity target measurement
CV and Pattern Recognition
Tracks fast objects precisely without missing details.