DebSDF: Delving into the Details and Bias of Neural Indoor Scene Reconstruction

TL;DR

DebSDF introduces an uncertainty-aware and bias-corrected neural implicit surface method that significantly improves detailed indoor scene reconstruction, especially for thin structures, by leveraging uncertainty modeling and bias-aware SDF transformations.

Contribution

The paper proposes a novel uncertainty modeling and bias-aware SDF approach to enhance neural indoor scene reconstruction, addressing limitations of monocular priors and volume rendering biases.

Findings

Outperforms previous methods in reconstructing thin structures.

Effectively excludes unreliable priors using uncertainty measures.

Achieves superior qualitative and quantitative results on challenging datasets.

Abstract

In recent years, the neural implicit surface has emerged as a powerful representation for multi-view surface reconstruction due to its simplicity and state-of-the-art performance. However, reconstructing smooth and detailed surfaces in indoor scenes from multi-view images presents unique challenges. Indoor scenes typically contain large texture-less regions, making the photometric loss unreliable for optimizing the implicit surface. Previous work utilizes monocular geometry priors to improve the reconstruction in indoor scenes. However, monocular priors often contain substantial errors in thin structure regions due to domain gaps and the inherent inconsistencies when derived independently from different views. This paper presents \textbf{DebSDF} to address these challenges, focusing on the utilization of uncertainty in monocular priors and the bias in SDF-based volume rendering. We propose an uncertainty modeling technique that associates larger uncertainties with larger errors in the monocular priors. High-uncertainty priors are then excluded from optimization to prevent bias. This uncertainty measure also informs an importance-guided ray sampling and adaptive smoothness regularization, enhancing the learning of fine structures. We further introduce a bias-aware signed distance function to density transformation that takes into account the curvature and the angle between the view direction and the SDF normals to reconstruct fine details better. Our approach has been validated through extensive experiments on several challenging datasets, demonstrating improved qualitative and quantitative results in reconstructing thin structures in indoor scenes, thereby outperforming previous work.