FreeTimeGS++: Secrets of Dynamic Gaussian Splatting and Their Principles

2026-05-04

AI Summary

This work addresses the lack of systematic understanding of the key mechanisms underlying existing 4D Gaussian Splatting (4DGS) methods, which has led to ambiguous principles and poor reproducibility. By constructing a controlled baseline, FreeTimeGS_ours, the study reveals for the first time the temporal slicing artifact induced by Gaussian duration and the inherent trade-off between photometric fidelity and spatiotemporal consistency. Building on these insights, the authors propose FreeTimeGS++, a principled framework incorporating gated marginalization and a neural velocity field to significantly enhance the stability and reproducibility of dynamic scene reconstruction. Experiments demonstrate that the method effectively reduces inter-run variance, and the authors release their code to establish a reliable benchmark for future research.

Abstract

The recent surge in 4D Gaussian Splatting (4DGS) has achieved impressive dynamic scene reconstruction. While these methods demonstrate remarkable performance, the specific drivers behind such gains remain less explored, making a systematic understanding of the underlying principles challenging. In this paper, we perform a comprehensive analysis of these hidden factors to provide a clearer perspective on the 4DGS framework. We first establish a controlled baseline, FreeTimeGS_ours, by formalizing and reproducing the heuristics of the state-of-the-art FreeTimeGS. Using this framework, we dissect 4DGS along its fundamental axes and uncover key secrets, including the emergent temporal partitioning driven by Gaussian durations and the discrepancy between photometric fidelity and spatiotemporal consistency. Based on these insights, we propose FreeTimeGS++, a principled method that employs gated marginalization and neural velocity fields to achieve superior stability and robust dynamic representations. Our approach yields reproducible results with reduced run-to-run variance. We will release our implementation to provide a reliable foundation for future 4DGS research.

Problem

• 4D Gaussian Splatting
• dynamic scene reconstruction
• temporal partitioning
• spatiotemporal consistency
• photometric fidelity

Innovation

• 4D Gaussian Splatting
• temporal partitioning
• gated marginalization
• neural velocity fields
• spatiotemporal consistency