NVGS：用于 3D 高斯泼溅遮挡剔除的神经可见性
NVGS: Neural Visibility for Occlusion Culling in 3D Gaussian Splatting
提出用小型共享 MLP 学习高斯点的视角相关可见性函数，在光栅化前剔除被遮挡图元，可直接集成到高斯泼溅渲染管线中提升 VRAM 效率和图像质量。
原文依据 learn the viewpoint-dependent visibility function of all Gaussians in a trained model using a small, shared MLP
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论3D 高斯泼溅可以利用视锥剔除和细节层次策略来加速包含大量图元的场景渲染。然而，高斯图元的半透明特性阻碍了另一种高效技术的应用：遮挡剔除。我们通过提出一种新方法来解决这一限制，该方法使用一个在场景中资产实例间共享的小型 MLP 来学习训练模型中所有高斯的视角相关可见性函数。通过在光栅化之前对视锥内的高斯查询该函数，我们的方法可以在渲染过程中丢弃被遮挡的图元。利用 Tensor Cores 进行高效计算，我们将这些神经查询直接集成到一个新颖的实例化软件光栅化器中。我们的方法结合实例化光栅化器和遮挡剔除 MLP，在 VRAM 使用和图像质量方面优于当前针对组合场景的最先进技术，并与现有的细节层次技术表现出互补特性。源代码可在 https://brent-zoomers.github.io/nvgs/ 获取。
英文原文摘要 1109 字符
3D Gaussian Splatting can exploit frustum culling and level-of-detail strategies to accelerate rendering of scenes containing a large number of primitives. However, the semi-transparent nature of Gaussians prevents the application of another highly effective technique: occlusion culling. We address this limitation by proposing a novel method to learn the viewpoint-dependent visibility function of all Gaussians in a trained model using a small, shared MLP across instances of an asset in a scene. By querying it for Gaussians within the viewing frustum prior to rasterization, our method can discard occluded primitives during rendering. Leveraging Tensor Cores for efficient computation, we integrate these neural queries directly into a novel instanced software rasterizer. Our approach outperforms the current state of the art for composed scenes in terms of VRAM usage and image quality, utilizing a combination of our instanced rasterizer and occlusion culling MLP, and exhibits complementary properties to existing LoD techniques. The source code is available at https://brent-zoomers.github.io/nvgs/