用椭球体实现精准实时体积渲染，无闪烁伪影且支持镜头模糊。
EVER: Exact Volumetric Ellipsoid Rendering for Real-time View Synthesis
- 以椭球体为基元，基于光线追踪实现精确体积渲染。
- 720p下在RTX4090上达30帧，大场景下比3DGS更清晰无伪影。
- 支持镜头畸变与景深模糊，适合高精度实时渲染应用。
我们提出精确体积椭球体渲染（EVER），一种用于实时可微发射仅体积渲染的方法。不同于基于光栅化的3D高斯点云（3DGS）方法，我们的基元表示方式可实现精确体积渲染，而非对3D高斯海报进行透明度合成。因此，与3DGS相比，我们的方法不会出现闪烁伪影和视图依赖密度问题，同时在NVIDIA RTX4090上实现约30 FPS的720p帧率。由于基于光线追踪，该方法可支持如景深模糊和相机畸变（例如鱼眼镜头）等效果，这些在光栅化中难以实现。我们在具有挑战性的大尺度场景（Zip-NeRF数据集）上验证，其准确性和一致性优于3DGS及后续视图一致渲染工作，是实时技术中结果最锐利的方案。
原文摘要 · Abstract (English)
We present Exact Volumetric Ellipsoid Rendering (EVER), a method for real-time differentiable emission-only volume rendering. Unlike recent rasterization based approach by 3D Gaussian Splatting (3DGS), our primitive based representation allows for exact volume rendering, rather than alpha compositing 3D Gaussian billboards. As such, unlike 3DGS our formulation does not suffer from popping artifacts and view dependent density, but still achieves frame rates of $\sim\!30$ FPS at 720p on an NVIDIA RTX4090. Since our approach is built upon ray tracing it enables effects such as defocus blur and camera distortion (e.g. such as from fisheye cameras), which are difficult to achieve by rasterization. We show that our method is more accurate with fewer blending issues than 3DGS and follow-up work on view-consistent rendering, especially on the challenging large-scale scenes from the Zip-NeRF dataset where it achieves sharpest results among real-time 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。