PermutoSDF: Fast Multi-View Reconstruction with Implicit Surfaces using Permutohedral Lattices
This work addresses the issue of overly smooth surfaces in multi-view reconstruction for computer vision and graphics applications, offering incremental improvements over existing SDF methods.
The paper tackles the problem of recovering accurate surface geometry in neural radiance-density field methods for novel-view rendering, achieving recovery of fine details like pores and wrinkles and rendering at 30 fps on an RTX 3090.
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