GAP: Gaussianize Any Point Clouds with Text Guidance

TL;DR

GAP introduces a text-guided method to convert raw point clouds into high-fidelity 3D Gaussians, enhancing 3D representation and rendering quality through multi-view optimization and surface constraints.

Contribution

The paper presents a novel framework that gaussianizes point clouds with text guidance, incorporating multi-view optimization, surface anchoring, and inpainting for improved 3D Gaussian generation.

Findings

Effective in synthetic and real-world scenarios

Produces high-fidelity 3D Gaussians from point clouds

Outperforms existing methods in quality and consistency

Abstract

3D Gaussian Splatting (3DGS) has demonstrated its advantages in achieving fast and high-quality rendering. As point clouds serve as a widely-used and easily accessible form of 3D representation, bridging the gap between point clouds and Gaussians becomes increasingly important. Recent studies have explored how to convert the colored points into Gaussians, but directly generating Gaussians from colorless 3D point clouds remains an unsolved challenge. In this paper, we propose GAP, a novel approach that gaussianizes raw point clouds into high-fidelity 3D Gaussians with text guidance. Our key idea is to design a multi-view optimization framework that leverages a depth-aware image diffusion model to synthesize consistent appearances across different viewpoints. To ensure geometric accuracy, we introduce a surface-anchoring mechanism that effectively constrains Gaussians to lie on the surfaces of 3D shapes during optimization. Furthermore, GAP incorporates a diffuse-based inpainting strategy that specifically targets at completing hard-to-observe regions. We evaluate GAP on the Point-to-Gaussian generation task across varying complexity levels, from synthetic point clouds to challenging real-world scans, and even large-scale scenes. Project Page: https://weiqi-zhang.github.io/GAP.