通过动态修剪与分组运动，让3D高斯溅射渲染快13倍还更清晰。
SpeeDe3DGS: Speedy Deformable 3D Gaussian Splatting with Temporal Pruning and Motion Grouping
- 按时间敏感度剪枝，只保留重要高斯点
- 渲染提速6.78倍，训练时间缩短2.53倍
- 适合需要实时动态3D重建的场景
动态扩展的3D高斯溅射（3DGS）通过神经运动场实现高质量重建，但每个高斯点独立推理导致计算开销大。基于DeformableGS，本文提出快速可变形3D高斯溅射（SpeeDe3DGS），引入三个互补模块：时间敏感性剪枝（TSP）通过时序聚合敏感性分析剔除低影响高斯点；时间敏感性采样（TSS）扰动时间戳以抑制伪影并提升时序一致性；GroupFlow将学习到的形变场压缩为共享的SE(3)变换，实现分组高效运动建模。在MonoDyGauBench的50个动态场景上，集成TSP和TSS使渲染速度平均提升6.78倍，同时仅用十分之一的原始高斯点维持神经场保真度；加入GroupFlow后，渲染速度达13.71倍加速，训练时间缩短2.53倍，优于所有基线，在速度与图像质量上均表现卓越。
原文摘要 · Abstract (English)
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.
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。