用稀疏体素实现高保真实时辐射场渲染，无需神经网络或3D高斯
Sparse Voxels Rasterization: Real-time High-fidelity Radiance Field Rendering
- 自适应分配稀疏体素，实现$65536^3$分辨率的细节重建
- 采用射线方向相关莫顿排序，提升渲染速度并消除闪烁伪影
- 兼容体素网格处理技术，适合后续扩展与实际应用
我们提出一种高效的辐射场渲染算法，基于自适应稀疏体素的光栅化过程，无需神经网络或3D高斯。首先，通过自适应显式分配稀疏体素至场景不同细节层级，在保持$65536^3$网格分辨率的同时实现高帧率渲染。其次，定制化光栅器利用射线方向依赖的莫顿排序，按正确深度顺序渲染体素，有效避免了高斯点阵中的常见闪烁伪影。相比先前无神经网络的体素模型，本方法在PSNR上提升超4dB，速度提升超过10倍，达到可比当前最先进水平的新视角合成效果。此外，该体素表示与基于网格的3D处理技术（如体素融合、体素池化、等值面提取）无缝兼容，为未来扩展和应用提供广泛基础。
原文摘要 · Abstract (English)
We propose an efficient radiance field rendering algorithm that incorporates a rasterization process on adaptive sparse voxels without neural networks or 3D Gaussians. There are two key contributions coupled with the proposed system. The first is to adaptively and explicitly allocate sparse voxels to different levels of detail within scenes, faithfully reproducing scene details with $65536^3$ grid resolution while achieving high rendering frame rates. Second, we customize a rasterizer for efficient adaptive sparse voxels rendering. We render voxels in the correct depth order by using ray direction-dependent Morton ordering, which avoids the well-known popping artifact found in Gaussian splatting. Our method improves the previous neural-free voxel model by over 4db PSNR and more than 10x FPS speedup, achieving state-of-the-art comparable novel-view synthesis results. Additionally, our voxel representation is seamlessly compatible with grid-based 3D processing techniques such as Volume Fusion, Voxel Pooling, and Marching Cubes, enabling a wide range of future extensions and applications.
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。