DensifyBeforehand: LiDAR-assisted Content-aware Densification for Efficient and Quality 3D Gaussian Splatting

TL;DR

This paper introduces a LiDAR-assisted, content-aware densification method for 3D Gaussian Splatting that improves visual quality and efficiency by initializing dense point clouds before optimization, reducing resource use.

Contribution

It proposes a novel densify beforehand approach combining LiDAR and monocular depth, bypassing adaptive density control to enhance 3D scene initialization and efficiency.

Findings

Achieves comparable visual quality to state-of-the-art methods.

Reduces resource consumption and training time significantly.

Effectively preserves regions of interest in complex scenes.

Abstract

This paper addresses the limitations of existing 3D Gaussian Splatting (3DGS) methods, particularly their reliance on adaptive density control, which can lead to floating artifacts and inefficient resource usage. We propose a novel densify beforehand approach that enhances the initialization of 3D scenes by combining sparse LiDAR data with monocular depth estimation from corresponding RGB images. Our ROI-aware sampling scheme prioritizes semantically and geometrically important regions, yielding a dense point cloud that improves visual fidelity and computational efficiency. This densify beforehand approach bypasses the adaptive density control that may introduce redundant Gaussians in the original pipeline, allowing the optimization to focus on the other attributes of 3D Gaussian primitives, reducing overlap while enhancing visual quality. Our method achieves comparable results to state-of-the-art techniques while significantly lowering resource consumption and training time. We validate our approach through extensive comparisons and ablation studies on four newly collected datasets, showcasing its effectiveness in preserving regions of interest in complex scenes.