通过建模SDF不确定性，提升仅用RGB图像的3D表面重建精度。
NeuDonatello: Uncertainty-Aware Framework for Accurate Neural SDF Learning
- 用蒙特卡洛采样建模空间变化的SDF不确定性
- 在纹理缺失区域自适应增强几何约束，避免错误重构
- 不确定性感知的密度转换参数，提升密度建模准确性
神经表面重建已成为从多视角图像恢复高质量3D表面的强大范式。然而，仅依靠RGB图像恢复精确几何结构仍具挑战性，原因在于无纹理区域、遮挡及场景固有模糊性带来的不确定性。现有方法常忽略此类不确定性，导致符号距离函数（SDF）估计不准确。本文提出NeuDonatello，一种新型框架，通过建模并利用SDF不确定性来改进表面重建。核心思想是采用蒙特卡洛采样策略建模空间变化的不确定性。基于此不确定性，设计自适应正则化，在RGB监督不可靠区域强化几何约束，避免错误重建。进一步引入不确定性感知的SDF-to-density转换尺度参数，条件于不确定性，实现空间变化密度的更准确建模。大量实验表明，NeuDonatello在仅使用带位姿的RGB图像下，达到当前最优重建精度，且在多样场景中表现稳健。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。