让3D高斯点云根据视角动态调整透明度，更好还原反光和反射效果。
VoD-3DGS: View-opacity-Dependent 3D Gaussian Splatting
- 为每个高斯点增加视角依赖的透明度矩阵，实现视点变化时的智能遮蔽
- 在多个基准数据集上达到当前最佳性能，渲染速度超60帧/秒
- 适合需要真实感材质表现的场景重建与可视化应用
从图像重建3D场景面临挑战，因光照与表面交互方式随观察角度和材质不同而变化。传统计算机图形学中，材质分为漫反射与镜面反射，对光的响应不同。标准3D高斯点阵模型难以表达视角依赖内容，无法区分物体本身与镜面反射产生的高光。本文提出在3D高斯点阵中引入额外对称矩阵，增强每个高斯点的透明度表示能力。该改进使部分高斯点能依据观察视角被抑制，从而更准确地呈现视角依赖的反射与高光，同时保持场景完整性。新模型在Mip-Nerf、Tanks&Temples、Deep Blending和Nerf-Synthetic数据集上均达到当前最优表现，渲染速度超过60FPS，内存开销仅小幅增加。
原文摘要 · Abstract (English)
Reconstructing a 3D scene from images is challenging due to the different ways light interacts with surfaces depending on the viewer's position and the surface's material. In classical computer graphics, materials can be classified as diffuse or specular, interacting with light differently. The standard 3D Gaussian Splatting model struggles to represent view-dependent content, since it cannot differentiate an object within the scene from the light interacting with its specular surfaces, which produce highlights or reflections. In this paper, we propose to extend the 3D Gaussian Splatting model by introducing an additional symmetric matrix to enhance the opacity representation of each 3D Gaussian. This improvement allows certain Gaussians to be suppressed based on the viewer's perspective, resulting in a more accurate representation of view-dependent reflections and specular highlights without compromising the scene's integrity. By allowing the opacity to be view dependent, our enhanced model achieves state-of-the-art performance on Mip-Nerf, Tanks&Temples, Deep Blending, and Nerf-Synthetic datasets without a significant loss in rendering speed, achieving >60FPS, and only incurring a minimal increase in memory used.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。