论文标题
PermutoSDF：使用置换式晶格使用隐式表面的快速多视图重建
PermutoSDF: Fast Multi-View Reconstruction with Implicit Surfaces using Permutohedral Lattices
论文作者
论文摘要
神经辐射密度的场方法已经越来越流行，这对于小说视图渲染的任务变得越来越流行。它们最近扩展到基于哈希的位置编码可确保快速训练和通过视觉令人愉悦的结果进行推断。但是，基于密度的方法努力恢复准确的表面几何形状。混合方法通过基于潜在的SDF优化密度来减轻此问题。但是，当前的SDF方法过于平滑，错过了细节细节。在这项工作中，我们将这两种工作的优势结合在基于新型哈希的隐式表面表示中。我们通过用置换式晶格替换编码体素哈希来提高两个区域的改进，从而更快地优化了，尤其是对于更高的尺寸。我们还提出了一种正规化方案，该方案对于恢复高频几何细节至关重要。我们在多个数据集上评估了我们的方法，并表明我们可以在仅使用RGB图像进行监督的同时恢复毛孔和皱纹的几何细节。此外，使用球体跟踪我们可以在RTX 3090上以30 fps呈现新颖的视图。代码可公开可用：https：//radualexandru.github.io/permuto_sdf
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 visually pleasing 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, especially for 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. Code is publicly available at: https://radualexandru.github.io/permuto_sdf
