3D surface reconstruction from images is essential for numerous applications. Recently, Neural Radiance Fields (NeRFs) have emerged as a promising framework for 3D modeling. However, NeRFs require accurate camera poses as input, and existing methods struggle to handle significantly noisy pose estimates (i.e., outliers), which are commonly encountered in real-world scenarios. To tackle this challenge, we present a novel approach that optimizes radiance fields with scene graphs to mitigate the influence of outlier poses. Our method incorporates an adaptive inlier-outlier confidence estimation scheme based on scene graphs, emphasizing images of high compatibility with the neighborhood and consistency in the rendering quality. We also introduce an effective intersection-over-union (IoU) loss to optimize the camera pose and surface geometry, together with a coarse-to-fine strategy to facilitate the training. Furthermore, we propose a new dataset containing typical outlier poses for a detailed evaluation. Experimental results on various datasets consistently demonstrate the effectiveness and superiority of our method over existing approaches, showcasing its robustness in handling outliers and producing high-quality 3D reconstructions. Our code and data are available at: \url{https://github.com/Iris-cyy/SG-NeRF}.

翻译：从图像进行三维表面重建对于众多应用至关重要。近年来，神经辐射场（NeRF）已成为一种有前景的三维建模框架。然而，NeRF需要准确的相机位姿作为输入，而现有方法难以处理现实场景中常见的显著噪声位姿估计（即异常值）。为应对这一挑战，我们提出了一种利用场景图优化辐射场以减轻异常位姿影响的新方法。我们的方法引入了一种基于场景图的自适应内点-外点置信度估计方案，强调与邻域兼容性高且渲染质量一致的图像。我们还提出了一种有效的交并比（IoU）损失函数，用于联合优化相机位姿与表面几何，并结合由粗到精的训练策略以促进优化过程。此外，我们构建了一个包含典型异常位姿的新数据集用于详细评估。在多个数据集上的实验结果一致证明了本方法相较于现有方案的有效性和优越性，展现了其在处理异常值和生成高质量三维重建结果方面的鲁棒性。我们的代码与数据公开于：\url{https://github.com/Iris-cyy/SG-NeRF}。