用事件流和物理规律增强3D高斯点云，实现大时空尺度下清晰的刚体运动重建。
PEGS: Physics-Event Enhanced Large Spatiotemporal Motion Reconstruction via 3D Gaussian Splatting
- 融合物理约束与事件流信息，在3D高斯点云中建模运动轨迹。
- 在多个场景下实现比主流方法更优的大时空运动重建效果。
- 适合需要高精度运动恢复的自动驾驶与机器人视觉任务。
大时空尺度下的刚体运动重建仍面临建模范式局限、严重运动模糊及物理一致性不足等挑战。本文提出 PEGS 框架，将物理先验与事件流增强整合至 3D Gaussian Splatting 管道中，实现去模糊的目标聚焦建模与运动恢复。设计了一种三重级联监督机制：通过加速度约束保证物理合理性，利用事件流提供高时间分辨率引导，采用卡尔曼正则化融合多源观测。此外，提出一种基于实时运动状态自适应调度训练过程的运动感知模拟退火策略。同时构建首个面向自然快速刚体运动、涵盖多种场景的 RGB-Event 配对数据集。实验表明，PEGS 在大时空尺度运动重建上显著优于主流动态方法。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。