PEGS: Physics-Event Enhanced Large Spatiotemporal Motion Reconstruction via 3D Gaussian Splatting
This work addresses motion reconstruction for applications like robotics or computer vision, but it appears incremental as it builds on existing 3D Gaussian Splatting with added components.
The paper tackles the challenge of reconstructing rigid motion over large spatiotemporal scales by proposing PEGS, a framework that integrates physical priors and event stream enhancement with 3D Gaussian Splatting, achieving superior performance compared to mainstream dynamic methods.
Reconstruction of rigid motion over large spatiotemporal scales remains a challenging task due to limitations in modeling paradigms, severe motion blur, and insufficient physical consistency. In this work, we propose PEGS, a framework that integrates Physical priors with Event stream enhancement within a 3D Gaussian Splatting pipeline to perform deblurred target-focused modeling and motion recovery. We introduce a cohesive triple-level supervision scheme that enforces physical plausibility via an acceleration constraint, leverages event streams for high-temporal resolution guidance, and employs a Kalman regularizer to fuse multi-source observations. Furthermore, we design a motion-aware simulated annealing strategy that adaptively schedules the training process based on real-time kinematic states. We also contribute the first RGB-Event paired dataset targeting natural, fast rigid motion across diverse scenarios. Experiments show PEGS's superior performance in reconstructing motion over large spatiotemporal scales compared to mainstream dynamic methods.