Reconstructing and predicting dynamic 3D scenes from multi-view videos is a foundational task for robotics, AR/VR, and digital twins. Recent physics-informed Gaussian Splatting methods achieve impressive future frame extrapolation but lack semantic awareness and suffer from large computational overhead. We introduce R5DGS, a framework that augments a physics-driven 4D Gaussian representation with compact Identity Encoding vectors, enabling precise Gaussian-to-object association. By constructing an offline CLIP-based object lookup table, we support open-vocabulary text prompting to retrieve and render object-specific Gaussians across arbitrary timestamps and viewpoints. Furthermore, we propose a rigid-body inference constraint that predicts and integrates physical dynamics exclusively for object centroids, propagating motion to associated Gaussians via relative transformations. This optimization yields a 11 FPS speedup during extrapolation without compromising trajectories plausibility.
@article{arxiv.2605.25909,
title = {R5DGS: Semantic-Aware 4D Gaussian Splatting with Rigid Body Constraints for Efficient Dynamic Scene Reconstruction},
author = {Denis Gridusov and Maxim Popov and Sergey Kolyubin},
journal= {arXiv preprint arXiv:2605.25909},
year = {2026}
}