Fine-detailed Neural Indoor Scene Reconstruction using multi-level importance sampling and multi-view consistency

TL;DR

FD-NeuS is a novel neural implicit surface reconstruction method that uses multi-level importance sampling and multi-view consistency to produce detailed indoor 3D models more efficiently.

Contribution

The paper introduces FD-NeuS, a new approach that leverages segmentation priors, importance sampling, and multi-view consistency for improved detailed 3D indoor scene reconstruction.

Findings

Outperforms existing methods in various indoor scenes.

Produces more detailed and accurate 3D reconstructions.

Reduces over-smoothing and optimization time compared to prior approaches.

Abstract

Recently, neural implicit 3D reconstruction in indoor scenarios has become popular due to its simplicity and impressive performance. Previous works could produce complete results leveraging monocular priors of normal or depth. However, they may suffer from over-smoothed reconstructions and long-time optimization due to unbiased sampling and inaccurate monocular priors. In this paper, we propose a novel neural implicit surface reconstruction method, named FD-NeuS, to learn fine-detailed 3D models using multi-level importance sampling strategy and multi-view consistency methodology. Specifically, we leverage segmentation priors to guide region-based ray sampling, and use piecewise exponential functions as weights to pilot 3D points sampling along the rays, ensuring more attention on important regions. In addition, we introduce multi-view feature consistency and multi-view normal consistency as supervision and uncertainty respectively, which further improve the reconstruction of details. Extensive quantitative and qualitative results show that FD-NeuS outperforms existing methods in various scenes.