Neural radiance-density field methods have become increasingly popular for the task of novel-view rendering. Their recent extension to hash-based positional encoding ensures fast training and inference with state-of-the-art results. However, density-based methods struggle with recovering accurate surface geometry. Hybrid methods alleviate this issue by optimizing the density based on an underlying SDF. However, current SDF methods are overly smooth and miss fine geometric details. In this work, we combine the strengths of these two lines of work in a novel hash-based implicit surface representation. We propose improvements to the two areas by replacing the voxel hash encoding with a permutohedral lattice which optimizes faster in three and higher dimensions. We additionally propose a regularization scheme which is crucial for recovering high-frequency geometric detail. We evaluate our method on multiple datasets and show that we can recover geometric detail at the level of pores and wrinkles while using only RGB images for supervision. Furthermore, using sphere tracing we can render novel views at 30 fps on an RTX 3090.

本文提出了一种包含哈希隐式表面表示的混合方法，通过使用转置矩阵晶格和正则化方案以优化这两个领域，旨在改善神经辐射密度场方法的表面几何恢复问题，并在多个数据集上评估效果。

使用排列哈密尔顿晶格的隐式曲面，实现快速多视角重建