Laplacian Analysis Meets Dynamics Modelling: Gaussian Splatting for 4D Reconstruction

TL;DR

This paper introduces a novel dynamic 3D Gaussian Splatting framework that combines spectral-aware Laplacian encoding, enhanced Gaussian dynamics, and adaptive splitting to improve 4D scene reconstruction fidelity.

Contribution

It presents a hybrid explicit-implicit model with spectral-aware encoding and adaptive strategies to better handle dynamic scene complexities in 4D reconstruction.

Findings

Achieves state-of-the-art reconstruction quality in dynamic scenes

Effectively balances motion detail preservation and deformation consistency

Demonstrates superior performance over existing methods

Abstract

While 3D Gaussian Splatting (3DGS) excels in static scene modeling, its extension to dynamic scenes introduces significant challenges. Existing dynamic 3DGS methods suffer from either over-smoothing due to low-rank decomposition or feature collision from high-dimensional grid sampling. This is because of the inherent spectral conflicts between preserving motion details and maintaining deformation consistency at different frequency. To address these challenges, we propose a novel dynamic 3DGS framework with hybrid explicit-implicit functions. Our approach contains three key innovations: a spectral-aware Laplacian encoding architecture which merges Hash encoding and Laplacian-based module for flexible frequency motion control, an enhanced Gaussian dynamics attribute that compensates for photometric distortions caused by geometric deformation, and an adaptive Gaussian split strategy guided by KDTree-based primitive control to efficiently query and optimize dynamic areas. Through extensive experiments, our method demonstrates state-of-the-art performance in reconstructing complex dynamic scenes, achieving better reconstruction fidelity.