用神经网络预测高斯点可见性，实现3D高斯溅射的遮挡剔除。
NVGS: Neural Visibility for Occlusion Culling in 3D Gaussian Splatting
- 用共享小MLP学习高斯点视角依赖的可见性函数。
- 在渲染前剔除遮挡点，降低显存占用并提升画质。
- 适合需要高效渲染海量高斯点的实时3D场景应用。
3D高斯溅射可利用视锥剔除和细节层次策略加速包含大量基本体的场景渲染。然而，高斯点的半透明特性阻碍了另一种高效技术——遮挡剔除的应用。本文提出一种新方法，通过在场景中同一资产实例间共享的小型MLP，学习训练后模型中所有高斯点的视角依赖可见性函数。在光栅化前查询视锥内高斯点的可见性，可提前剔除被遮挡的基本体。借助张量核心实现高效计算，将神经查询直接集成到新型实例化软件光栅器中。该方法在组合场景下相比现有最优方案，在显存使用和图像质量上均表现更优，且与现有层级细节技术具有互补性。
原文摘要 · Abstract (English)
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.
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。