We study the problem of reconstructing 3D feature curves of an object from a set of calibrated multi-view images. To do so, we learn a neural implicit field representing the density distribution of 3D edges which we refer to as Neural Edge Field (NEF). Inspired by NeRF, NEF is optimized with a view-based rendering loss where a 2D edge map is rendered at a given view and is compared to the ground-truth edge map extracted from the image of that view. The rendering-based differentiable optimization of NEF fully exploits 2D edge detection, without needing a supervision of 3D edges, a 3D geometric operator or cross-view edge correspondence. Several technical designs are devised to ensure learning a range-limited and view-independent NEF for robust edge extraction. The final parametric 3D curves are extracted from NEF with an iterative optimization method. On our benchmark with synthetic data, we demonstrate that NEF outperforms existing state-of-the-art methods on all metrics. Project page: https://yunfan1202.github.io/NEF/.

翻译：我们研究从一组已标定的多视角图像中重建物体三维特征曲线的问题。为此，我们学习了一个表征三维边缘密度分布的神经隐式场，称为神经边缘场（NEF）。受NeRF启发，NEF通过基于视角的渲染损失进行优化：在给定视角下渲染二维边缘图，并与该视角图像中提取的真实边缘图进行比较。基于渲染的可微分优化充分利用了二维边缘检测，无需三维边缘监督、三维几何算子或跨视角边缘对应。我们设计了若干技术方案，以确保学习到的NEF具有范围受限和视角无关的特性，从而实现鲁棒的边缘提取。最终通过迭代优化方法从NEF中提取参数化三维曲线。在基于合成数据的基准测试中，我们证明NEF在所有指标上均优于现有最先进方法。项目主页：https://yunfan1202.github.io/NEF/。