NerVE: Neural Volumetric Edges for Parametric Curve Extraction from Point Cloud
This addresses a fundamental problem in 3D vision and geometry processing for applications like computer-aided design, but it is incremental as it builds on volumetric learning frameworks.
The paper tackled the problem of extracting parametric edge curves from point clouds, which is challenging due to noisy keypoint detection in existing methods, and proposed NerVE, a neural volumetric edge representation that outperforms previous state-of-the-art methods on the ABC dataset.
Extracting parametric edge curves from point clouds is a fundamental problem in 3D vision and geometry processing. Existing approaches mainly rely on keypoint detection, a challenging procedure that tends to generate noisy output, making the subsequent edge extraction error-prone. To address this issue, we propose to directly detect structured edges to circumvent the limitations of the previous point-wise methods. We achieve this goal by presenting NerVE, a novel neural volumetric edge representation that can be easily learned through a volumetric learning framework. NerVE can be seamlessly converted to a versatile piece-wise linear (PWL) curve representation, enabling a unified strategy for learning all types of free-form curves. Furthermore, as NerVE encodes rich structural information, we show that edge extraction based on NerVE can be reduced to a simple graph search problem. After converting NerVE to the PWL representation, parametric curves can be obtained via off-the-shelf spline fitting algorithms. We evaluate our method on the challenging ABC dataset. We show that a simple network based on NerVE can already outperform the previous state-of-the-art methods by a great margin. Project page: https://dongdu3.github.io/projects/2023/NerVE/.