GeoTexDensifier: Geometry-Texture-Aware Densification for High-Quality Photorealistic 3D Gaussian Splatting

2024-12-22

arXiv.org

AI Summary

To address geometric distortion and texture blurring in 3D Gaussian Splatting (3DGS) reconstruction caused by sparse or non-uniform Gaussian distribution, this paper proposes a geometry-texture co-densification framework. Our method innovatively integrates monocular depth priors and surface normal constraints for robust geometric validation; designs a texture-richness-aware densification strategy to suppress noise in low-texture regions; and introduces depth-ratio change verification, normal-guided Gaussian splitting, and auxiliary texture density map modeling. Evaluated on multiple standard benchmarks, our approach achieves significant improvements in novel-view synthesis metrics—PSNR, SSIM, and LPIPS—while generating 3DGS models with high-fidelity geometry and fine-grained texture. The resulting reconstructions attain state-of-the-art (SOTA) rendering quality.

Technology Category

• Computer Vision: 3D Computer Vision
• Machine Learning: Deep Generative Models & Autoencoders
• Search and Optimization: Non-convex Optimization

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

3D Gaussian Splatting (3DGS) has recently attracted wide attentions in various areas such as 3D navigation, Virtual Reality (VR) and 3D simulation, due to its photorealistic and efficient rendering performance. High-quality reconstrution of 3DGS relies on sufficient splats and a reasonable distribution of these splats to fit real geometric surface and texture details, which turns out to be a challenging problem. We present GeoTexDensifier, a novel geometry-texture-aware densification strategy to reconstruct high-quality Gaussian splats which better comply with the geometric structure and texture richness of the scene. Specifically, our GeoTexDensifier framework carries out an auxiliary texture-aware densification method to produce a denser distribution of splats in fully textured areas, while keeping sparsity in low-texture regions to maintain the quality of Gaussian point cloud. Meanwhile, a geometry-aware splitting strategy takes depth and normal priors to guide the splitting sampling and filter out the noisy splats whose initial positions are far from the actual geometric surfaces they aim to fit, under a Validation of Depth Ratio Change checking. With the help of relative monocular depth prior, such geometry-aware validation can effectively reduce the influence of scattered Gaussians to the final rendering quality, especially in regions with weak textures or without sufficient training views. The texture-aware densification and geometry-aware splitting strategies are fully combined to obtain a set of high-quality Gaussian splats. We experiment our GeoTexDensifier framework on various datasets and compare our Novel View Synthesis results to other state-of-the-art 3DGS approaches, with detailed quantitative and qualitative evaluations to demonstrate the effectiveness of our method in producing more photorealistic 3DGS models.

Problem

• Improves 3D Gaussian splat distribution for realistic rendering
• Enhances geometry and texture detail in 3D reconstruction
• Reduces noise from scattered splats in weak-texture areas

Innovation

• Texture-aware densification for richer splats in textured areas
• Geometry-aware splitting using depth and normal priors
• Combined strategy reduces noise and improves rendering quality