We represent these edges as a collection of parametric curves(i.e., lines, circles, and B-splines).

We introduce an end-to-end learnable technique to robustly identify feature edges in 3D point cloud data. We represent these edges as a collection of parametric curves (i.e.,~lines, circles, and B-splines). Accordingly, our deep neural network, coined PIE-NET, is trained for parametric inference of edges. The network relies on a region proposal architecture, where a first module proposes an over-complete collection of edge and corner points, and a second module ranks each proposal to decide whether it should be considered. We train and evaluate our method on the ABC dataset, a large dataset of CAD models, and compare our results to those produced by traditional (non-learning) processing pipelines, as well as a recent deep learning based edge detector (EC-NET). Our results significantly improve over the state-of-the-art from both a quantitative and qualitative standpoint.

We thank all the reviewers for their insightful comments and encouraging remarks. Our innovation is not intended to be the development of new ML techniques, but lends itself to the application setting. Hence, the value of our contribution is not as a "final say", but in setting up a strong baseline to entice "Only evaluated on one dataset, limiting applications (R3)." Sorry, this is not quite true. Paper should be more self-contained (R1 & R2).

The reviewers felt that this paper provides an interesting and novel approach. The demonstrated approach outperforms the previous state of the art by a large margin. The main concern by reviewers is whether this paper is appropriate for a machine learning conference. All reviewers agree that the submission is a strong application paper that would be a strong submission for a computer vision, graphics, or computational geometry conference. However, the reviewers questioned whether the machine learning novelty in this paper is sufficient for a machine learning conference.

We introduce an end-to-end learnable technique to robustly identify feature edges in 3D point cloud data. We represent these edges as a collection of parametric curves (i.e., lines, circles, and B-splines). Accordingly, our deep neural network, coined PIE-NET, is trained for parametric inference of edges. The network relies on a "region proposal" architecture, where a first module proposes an over-complete collection of edge and corner points, and a second module ranks each proposal to decide whether it should be considered. We train and evaluate our method on the ABC dataset, a large dataset of CAD models, and compare our results to those produced by traditional (non-learning) processing pipelines, as well as a recent deep learning based edge detector (EC-NET).