PEGS: Physics-Event Enhanced Large Spatiotemporal Motion Reconstruction via 3D Gaussian Splatting
By: Yijun Xu , Jingrui Zhang , Hongyi Liu and more
Potential Business Impact:
Makes blurry videos clear and tracks fast movement.
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.
Similar Papers
PMGS: Reconstruction of Projectile Motion across Large Spatiotemporal Spans via 3D Gaussian Splatting
CV and Pattern Recognition
**Tracks fast-moving objects in 3D videos.**
EGS-SLAM: RGB-D Gaussian Splatting SLAM with Events
Robotics
Makes 3D pictures clear even when moving fast.
Physics-Informed Deformable Gaussian Splatting: Towards Unified Constitutive Laws for Time-Evolving Material Field
CV and Pattern Recognition
Makes videos look real by understanding how things move.