Jiang Hanqing, Xiang Xiaojun, Sun Han, Li Hongjie, Zhou Liyang, Zhang Xiaoyu, Zhang Guofeng
IEEE Trans Vis Comput Graph. 2026 Mar;32(3):2671-2683. doi: 10.1109/TVCG.2025.3644697.
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.
3D高斯点渲染（3DGS）由于其逼真的渲染性能和高效性，最近在3D导航、虚拟现实（VR）和3D模拟等各个领域引起了广泛关注。3DGS的高质量重建依赖于足够数量的点以及这些点的合理分布，以拟合真实的几何表面和纹理细节，而这是一个具有挑战性的问题。我们提出了GeoTexDensifier，一种新颖的几何纹理感知致密化策略，用于重建高质量的高斯点，使其更好地符合场景的几何结构和纹理丰富度。具体而言，我们的GeoTexDensifier框架执行一种辅助的纹理感知致密化方法，以在全纹理区域产生更密集的点分布，同时在低纹理区域保持稀疏性以维持高斯点云的质量。与此同时，一种几何感知分裂策略利用深度和法线先验来指导分裂采样，并在深度比变化验证检查下滤除初始位置远离其旨在拟合的实际几何表面的噪声点。借助相对单目深度先验，这种几何感知验证可以有效减少散射高斯点对最终渲染质量的影响，特别是在纹理较弱或没有足够训练视图的区域。纹理感知致密化和几何感知分裂策略被充分结合，以获得一组高质量的高斯点。我们在各种数据集上对我们的GeoTexDensifier框架进行了实验，并将我们的新视图合成结果与其他最新的3DGS方法进行了比较，通过详细的定量和定性评估来证明我们的方法在生成更逼真的3DGS模型方面的有效性。
