GDGS: 3D Gaussian Splatting Via Geometry-Guided Initialization And Dynamic Density Control

2025-06-30

AI Summary

3D Gaussian Splatting (3DGS) suffers from three key limitations: coarse initialization, susceptibility to local minima during optimization, and poor convergence to precise surfaces due to unstructured Gaussian distributions—exacerbated by the absence of geometry-aware adaptive density control. To address these, we propose a three-stage framework: (1) geometry-guided initialization leveraging depth and surface normal priors to generate structurally consistent initial Gaussians; (2) surface-aligned optimization incorporating normal alignment regularization to enhance geometric fidelity; and (3) region-complexity-driven dynamic density control that adaptively inserts, removes, or rescales Gaussian ellipsoids based on local geometric complexity. Experiments demonstrate that our method achieves rendering quality on par with or surpassing state-of-the-art methods on complex scenes, accelerates convergence by ~35%, and significantly improves detail preservation and real-time performance (≥30 FPS).

Technology Category

• Computer Vision: 3D Computer Vision
• Search and Optimization: Sampling/Simulation-based Search
• Machine Learning: Optimization

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

We propose a method to enhance 3D Gaussian Splatting (3DGS)~cite{Kerbl2023}, addressing challenges in initialization, optimization, and density control. Gaussian Splatting is an alternative for rendering realistic images while supporting real-time performance, and it has gained popularity due to its explicit 3D Gaussian representation. However, 3DGS heavily depends on accurate initialization and faces difficulties in optimizing unstructured Gaussian distributions into ordered surfaces, with limited adaptive density control mechanism proposed so far. Our first key contribution is a geometry-guided initialization to predict Gaussian parameters, ensuring precise placement and faster convergence. We then introduce a surface-aligned optimization strategy to refine Gaussian placement, improving geometric accuracy and aligning with the surface normals of the scene. Finally, we present a dynamic adaptive density control mechanism that adjusts Gaussian density based on regional complexity, for visual fidelity. These innovations enable our method to achieve high-fidelity real-time rendering and significant improvements in visual quality, even in complex scenes. Our method demonstrates comparable or superior results to state-of-the-art methods, rendering high-fidelity images in real time.

Problem

• Enhance 3D Gaussian Splatting initialization and optimization
• Optimize unstructured Gaussian distributions into ordered surfaces
• Improve adaptive density control for complex scenes

Innovation

• Geometry-guided initialization for precise placement
• Surface-aligned optimization for geometric accuracy
• Dynamic density control for regional complexity