Search papers, labs, and topics across Lattice.
NeuDonatello is an innovative framework that addresses the challenges of neural surface reconstruction by incorporating uncertainty modeling into the learning of signed distance functions (SDF). By utilizing a Monte Carlo sampling strategy to capture spatially varying uncertainties, the framework adaptively strengthens geometric constraints in areas where RGB supervision is unreliable, leading to improved surface accuracy. Experimental results show that NeuDonatello achieves state-of-the-art reconstruction performance across diverse scenes using only posed RGB images, significantly enhancing the reliability of 3D surface recovery.
By integrating uncertainty modeling into SDF learning, NeuDonatello significantly boosts the accuracy of 3D surface reconstruction from RGB images, even in challenging scenarios.
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.
