1000+ FPS 4D高斯潑濺用於動態場景渲染

1000+ FPS 4D Gaussian Splatting for Dynamic Scene Rendering

March 20, 2025

作者: Yuheng Yuan, Qiuhong Shen, Xingyi Yang, Xinchao Wang

cs.AI

摘要

4D高斯溅射（4DGS）作为重建动态场景的方法，近期获得了广泛关注。尽管其重建质量卓越，但4DGS通常需要大量存储空间，且渲染速度较慢。在本研究中，我们深入探讨了这些问题，并识别出两个关键的时间冗余来源。（Q1）短寿命高斯：4DGS使用大量时间跨度较短的高斯来表示场景动态，导致高斯数量过多。（Q2）非活跃高斯：在渲染时，每帧仅有一小部分高斯参与贡献。尽管如此，所有高斯在光栅化过程中均被处理，造成了冗余的计算开销。针对这些冗余，我们提出了4DGS-1K，它能在现代GPU上以超过1000 FPS的速度运行。对于Q1，我们引入了时空变化评分这一新的剪枝标准，有效去除短寿命高斯，同时鼓励4DGS使用时间跨度更长的高斯来捕捉场景动态。对于Q2，我们存储了连续帧中活跃高斯的掩码，显著减少了渲染中的冗余计算。与原始4DGS相比，我们的方法在复杂动态场景上实现了存储空间减少41倍、光栅化速度提升9倍的效果，同时保持了相当的视觉质量。详情请访问我们的项目页面：https://4DGS-1K.github.io。

English

4D Gaussian Splatting (4DGS) has recently gained considerable attention as a method for reconstructing dynamic scenes. Despite achieving superior quality, 4DGS typically requires substantial storage and suffers from slow rendering speed. In this work, we delve into these issues and identify two key sources of temporal redundancy. (Q1) Short-Lifespan Gaussians: 4DGS uses a large portion of Gaussians with short temporal span to represent scene dynamics, leading to an excessive number of Gaussians. (Q2) Inactive Gaussians: When rendering, only a small subset of Gaussians contributes to each frame. Despite this, all Gaussians are processed during rasterization, resulting in redundant computation overhead. To address these redundancies, we present 4DGS-1K, which runs at over 1000 FPS on modern GPUs. For Q1, we introduce the Spatial-Temporal Variation Score, a new pruning criterion that effectively removes short-lifespan Gaussians while encouraging 4DGS to capture scene dynamics using Gaussians with longer temporal spans. For Q2, we store a mask for active Gaussians across consecutive frames, significantly reducing redundant computations in rendering. Compared to vanilla 4DGS, our method achieves a 41times reduction in storage and 9times faster rasterization speed on complex dynamic scenes, while maintaining comparable visual quality. Please see our project page at https://4DGS-1K.github.io.