DensifyBeforehand: LiDAR-assisted Content-aware Densification for Efficient and Quality 3D Gaussian Splatting
This addresses efficiency and quality issues in 3D reconstruction for computer vision applications, representing an incremental improvement over existing 3D Gaussian Splatting methods.
This paper tackles the problem of floating artifacts and inefficient resource usage in 3D Gaussian Splatting by proposing a densify beforehand approach that uses LiDAR data and monocular depth estimation to improve scene initialization. The method achieves comparable results to state-of-the-art techniques while significantly lowering resource consumption and training time.
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.