NeuDonatello: Uncertainty-Aware Framework for Accurate Neural SDF Learning

2026-08-26

AI Summary

为解决从RGB图像恢复准确3D表面的难题，NeuDonatello通过建模SDF不确定性并采用自适应正则化方法，提高了表面重建精度。

Abstract

Neural surface reconstruction has emerged as a powerful paradigm for recovering high-quality 3D surfaces from multi-view images. However, recovering accurate geometry solely from RGB images remains challenging due to uncertainties arising from textureless regions, occlusions, and inherent scene ambiguities. Existing methods often overlook such uncertainties, leading to inaccurate estimates of the signed distance function (SDF). We introduce NeuDonatello, a novel framework that models and leverages SDF uncertainty to improve surface reconstruction. Central to our approach is to model spatially varying uncertainty using a Monte Carlo sampling strategy. Using this uncertainty, we develop an adaptive regularization that selectively strengthens geometric constraints where RGB supervision is unreliable, avoiding incorrect surface reconstruction. We further introduce an uncertainty-aware scale parameter for the SDF-to-density conversion. Conditioned on uncertainty, this design enables more accurate modeling of spatially varying densities. Extensive experiments demonstrate that NeuDonatello achieves state-of-the-art reconstruction accuracy, with robust performance across diverse scenes using only posed RGB images.

Problem

• Neural surface reconstruction
• uncertainties
• signed distance function (SDF)
• textureless regions
• occlusions

Innovation

• Uncertainty-Aware Framework
• Monte Carlo Sampling
• Adaptive Regularization
• SDF-to-Density Conversion