NeuDonatello: Uncertainty-Aware Framework for Accurate Neural SDF Learning

Researchers introduced NeuDonatello, a framework that models signed distance function (SDF) uncertainty via Monte Carlo sampling to improve neural surface reconstruction from multi-view RGB images. The method uses adaptive regularization and an uncertainty-aware scale parameter for SDF-to-density conversion, achieving state-of-the-art accuracy across diverse scenes. The work is detailed in arXiv paper 2608.26504.

arXiv:2608.26504v1 Announce Type: new 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.