TSDF-Sampling: Efficient Sampling for Neural Surface Field using Truncated Signed Distance Field

TL;DR

This paper presents TSDF-Sampling, a method that significantly accelerates neural surface reconstruction by reducing sampling requirements using Truncated Signed Distance Fields, maintaining high quality and broad applicability.

Contribution

Introduces a novel TSDF-based sampling method that improves inference speed and robustness across neural surface models without sacrificing quality.

Findings

Achieves 11-fold faster inference speed.

Maintains high rendering quality with fewer samples.

Robustly integrates with various neural surface models.

Abstract

Multi-view neural surface reconstruction has exhibited impressive results. However, a notable limitation is the prohibitively slow inference time when compared to traditional techniques, primarily attributed to the dense sampling, required to maintain the rendering quality. This paper introduces a novel approach that substantially reduces the number of samplings by incorporating the Truncated Signed Distance Field (TSDF) of the scene. While prior works have proposed importance sampling, their dependence on initial uniform samples over the entire space makes them unable to avoid performance degradation when trying to use less number of samples. In contrast, our method leverages the TSDF volume generated only by the trained views, and it proves to provide a reasonable bound on the sampling from upcoming novel views. As a result, we achieve high rendering quality by fully exploiting the continuous neural SDF estimation within the bounds given by the TSDF volume. Notably, our method is the first approach that can be robustly plug-and-play into a diverse array of neural surface field models, as long as they use the volume rendering technique. Our empirical results show an 11-fold increase in inference speed without compromising performance. The result videos are available at our project page: https://tsdf-sampling.github.io/