EVER：用于实时视图合成的精确体积椭球渲染

EVER: Exact Volumetric Ellipsoid Rendering for Real-time View Synthesis

October 2, 2024

作者: Alexander Mai, Peter Hedman, George Kopanas, Dor Verbin, David Futschik, Qiangeng Xu, Falko Kuester, Jon Barron, Yinda Zhang

cs.AI

摘要

我们提出了精确体积椭球渲染（EVER），这是一种用于实时可微的仅发射体积渲染的方法。与最近基于光栅化的3D高斯飞溅（3DGS）方法不同，我们基于基元的表示允许进行精确的体积渲染，而不是对3D高斯广告牌进行alpha合成。因此，与3DGS不同，我们的公式不会出现跳动伪影和视角相关密度问题，但仍然能够在NVIDIA RTX4090上以720p分辨率实现约30 FPS的帧率。由于我们的方法基于光线追踪，因此可以实现诸如焦外模糊和相机失真（例如来自鱼眼相机）等效果，这些效果在光栅化中难以实现。我们展示了我们的方法比3DGS更准确，融合问题更少，并且在视角一致渲染的后续工作中，特别是在Zip-NeRF数据集中具有挑战性的大规模场景中，我们的方法实现了实时技术中最清晰的结果。

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.