Fully Explicit Dynamic Gaussian Splatting

TL;DR

This paper introduces Ex4DGS, a method for dynamic scene rendering using explicit 4D Gaussian splatting that separates static and dynamic elements, interpolates motions, and improves efficiency and quality.

Contribution

The paper proposes a novel explicit 4D Gaussian splatting approach that explicitly models dynamic motions with interpolation and a progressive training scheme, enabling fast and high-quality dynamic scene rendering.

Findings

Achieves 62 fps rendering on a single GPU.

Outperforms previous methods in rendering quality.

Effectively models dynamic motions with explicit interpolation.

Abstract

3D Gaussian Splatting has shown fast and high-quality rendering results in static scenes by leveraging dense 3D prior and explicit representations. Unfortunately, the benefits of the prior and representation do not involve novel view synthesis for dynamic motions. Ironically, this is because the main barrier is the reliance on them, which requires increasing training and rendering times to account for dynamic motions. In this paper, we design a Explicit 4D Gaussian Splatting(Ex4DGS). Our key idea is to firstly separate static and dynamic Gaussians during training, and to explicitly sample positions and rotations of the dynamic Gaussians at sparse timestamps. The sampled positions and rotations are then interpolated to represent both spatially and temporally continuous motions of objects in dynamic scenes as well as reducing computational cost. Additionally, we introduce a progressive training scheme and a point-backtracking technique that improves Ex4DGS's convergence. We initially train Ex4DGS using short timestamps and progressively extend timestamps, which makes it work well with a few point clouds. The point-backtracking is used to quantify the cumulative error of each Gaussian over time, enabling the detection and removal of erroneous Gaussians in dynamic scenes. Comprehensive experiments on various scenes demonstrate the state-of-the-art rendering quality from our method, achieving fast rendering of 62 fps on a single 2080Ti GPU.