几何先验引导的野外神经隐式表面重建
Geometric Prior-Guided Neural Implicit Surface Reconstruction in the Wild
AI总结：
针对野外图像中光照变化、瞬态遮挡及表面约束不足的问题，提出融合 SfM 稀疏点、位移补偿、鲁棒法向与边缘及多视角一致性约束的神经隐式表面重建方法。
摘要：
使用体渲染技术的神经隐式表面重建近来在从多张二维图像创建高保真表面方面取得了重大进展。然而，当前方法主要面向光照一致的场景，在存在瞬态遮挡或外观变化的非受控环境中难以准确重建三维几何。虽然一些基于神经辐射场（NeRF）的变体能够更好地处理复杂场景中的光度变化和瞬态物体，但由于表面约束有限，它们是为新视角合成而非精确表面重建设计的。为克服这一局限，我们提出一种新方法，将多种几何约束应用于隐式表面优化过程，从而能够从非约束图像集合中获得更准确的重建。首先，我们利用来自运动恢复结构（SfM）的稀疏三维点来细化重建表面的有符号距离函数估计，并通过位移补偿来适应稀疏点中的噪声。此外，我们采用由法向预测器得到的鲁棒法向先验，并通过边缘先验滤波和多视角一致性约束加以增强，以改善与实际表面几何的对齐。在 Heritage-Recon 基准和其他数据集上的大量测试表明，所提方法能够从野外图像中准确重建表面，与现有技术相比，可生成具有更优精度和细粒度的几何。我们的方法能够对各类地标进行高质量三维重建，使其适用于文化遗产地数字保存等多种场景。
英文摘要：
Neural implicit surface reconstruction using volume rendering techniques has recently achieved significant advancements in creating high-fidelity surfaces from multiple 2D images. However, current methods primarily target scenes with consistent illumination and struggle to accurately reconstruct 3D geometry in uncontrolled environments with transient occlusions or varying appearances. While some neural radiance field (NeRF)-based variants can better manage photometric variations and transient objects in complex scenes, they are designed for novel view synthesis rather than precise surface reconstruction due to limited surface constraints. To overcome this limitation, we introduce a novel approach that applies multiple geometric constraints to the implicit surface optimization process, enabling more accurate reconstructions from unconstrained image collections. First, we utilize sparse 3D points from structure-from-motion (SfM) to refine the signed distance function estimation for the reconstructed surface, with a displacement compensation to accommodate noise in the sparse points. Additionally, we employ robust normal priors derived from a normal predictor, enhanced by edge prior filtering and multi-view consistency constraints, to improve alignment with the actual surface geometry. Extensive testing on the Heritage-Recon benchmark and other datasets has shown that the proposed method can accurately reconstruct surfaces from in-the-wild images, yielding geometries with superior accuracy and granularity compared to existing techniques. Our approach enables high-quality 3D reconstruction of various landmarks, making it applicable to diverse scenarios such as digital preservation of cultural heritage sites.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
