SpeeDe3DGS: Speedy Deformable 3D Gaussian Splatting with Temporal Pruning and Motion Grouping

TL;DR

SpeeDe3DGS introduces a set of modules that significantly accelerate dynamic 3D Gaussian Splatting rendering and training without sacrificing quality, by pruning, sampling, and grouping motion data.

Contribution

The paper presents SpeeDe3DGS, a novel framework that combines three modules to improve efficiency of dynamic 3D Gaussian Splatting with minimal quality loss.

Findings

Achieves 13.71× faster rendering on average.

Reduces training time by 2.53×.

Maintains high fidelity comparable to baseline methods.

Abstract

Dynamic extensions of 3D Gaussian Splatting (3DGS) achieve high-quality reconstructions through neural motion fields, but per-Gaussian neural inference makes these models computationally expensive. Building on DeformableGS, we introduce Speedy Deformable 3D Gaussian Splatting (SpeeDe3DGS), which bridges this efficiency-fidelity gap through three complementary modules: Temporal Sensitivity Pruning (TSP) removes low-impact Gaussians via temporally aggregated sensitivity analysis, Temporal Sensitivity Sampling (TSS) perturbs timestamps to suppress floaters and improve temporal coherence, and GroupFlow distills the learned deformation field into shared SE(3) transformations for efficient groupwise motion. On the 50 dynamic scenes in MonoDyGauBench, integrating TSP and TSS into DeformableGS accelerates rendering by 6.78$\times$ on average while maintaining neural-field fidelity and using 10$\times$ fewer primitives. Adding GroupFlow culminates in 13.71$\times$ faster rendering and 2.53$\times$ shorter training, surpassing all baselines in speed while preserving superior image quality.