Leveraging Geometric Prior Uncertainty and Complementary Constraints for High-Fidelity Neural Indoor Surface Reconstruction

TL;DR

GPU-SDF is a neural implicit framework that improves indoor surface reconstruction by explicitly estimating geometric prior uncertainty and applying complementary constraints, leading to finer detail recovery.

Contribution

It introduces a self-supervised uncertainty estimation module and an uncertainty-guided loss, enhancing existing neural surface reconstruction methods.

Findings

Enhanced recovery of fine details and thin structures.

Effective handling of noisy and unreliable priors.

Improved boundary and geometric coherence in reconstructions.

Abstract

Neural implicit surface reconstruction with signed distance function has made significant progress, but recovering fine details such as thin structures and complex geometries remains challenging due to unreliable or noisy geometric priors. Existing approaches rely on implicit uncertainty that arises during optimization to filter these priors, which is indirect and inefficient, and masking supervision in high-uncertainty regions further leads to under-constrained optimization. To address these issues, we propose GPU-SDF, a neural implicit framework for indoor surface reconstruction that leverages geometric prior uncertainty and complementary constraints. We introduce a self-supervised module that explicitly estimates prior uncertainty without auxiliary networks. Based on this estimation, we design an uncertainty-guided loss that modulates prior influence rather than discarding it, thereby retaining weak but informative cues. To address regions with high prior uncertainty, GPU-SDF further incorporates two complementary constraints: an edge distance field that strengthens boundary supervision and a multi-view consistency regularization that enforces geometric coherence. Extensive experiments confirm that GPU-SDF improves the reconstruction of fine details and serves as a plug-and-play enhancement for existing frameworks. Source code will be available at https://github.com/IRMVLab/GPU-SDF