EC-Net: an Edge-aware Point set Consolidation Network

By Lequan Yu, Chi-Wing Fu, Daniel Cohen-Or, P. Heng. European Conference on Computer Vision, 2018

296 citations recorded by the source corpus.

Point clouds obtained from 3D scans are typically sparse, irregular, and noisy, and required to be consolidated. In this paper, we present the first deep learning based edge-aware technique to facilitate the consolidation of point clouds. We design our network to process points grouped in local patches, and train it to learn and help consolidate points, deliberately for edges. To achieve this, we formulate a regression component to simultaneously recover 3D point coordinates and point-to-edge distances from upsampled features, and an edge-aware joint loss function to directly minimize distances from output points to 3D meshes and to edges. Compared with previous neural network based works, our consolidation is edge-aware. During the synthesis, our network can attend to the detected sharp edges and enable more accurate 3D reconstructions. Also, we trained our network on virtual scanned point clouds, demonstrated the performance of our method on both synthetic and real point clouds, presented various surface reconstruction results, and showed how our method outperforms the state-of-the-arts.

Subfields: Computational Mechanics, Computer Graphics and Computer-Aided Design

View Paper: https://www.semanticscholar.org/paper/5496bcba55fb155c331228efe65f3b94696bf611

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Mechanics

1. Daniel Cohen-Or
2. Olga Sorkine-Hornung
3. P. Heng
4. Chi-Wing Fu
5. Shihao Wu
6. Ruihui Li
7. Yifan Wang
8. Hui Huang

In Computer Graphics and Computer-Aided Design

1. Daniel Cohen-Or
2. Olga Sorkine-Hornung
3. P. Heng
4. Chi-Wing Fu
5. Shihao Wu
6. Ruihui Li
7. Yifan Wang
8. Hui Huang

Citations in the corpus

• Differentiable surface splatting for point-based geometry processing (2019, background): “…points and visibility changes and enables large deformation including topology changes. properties from noisy and outlier-ridden point sets; EC-Net [Yu et al. 2018] learns point cloud consolidation and restoration of sharp features by minimizing a point-to-edge distance, but it requires edge…”
• PU-GAN: A Point Cloud Upsampling Adversarial Network (2019, methodology): “Later, they introduced EC-Net [39] for edge-aware point cloud upsampling by formulating an edge-aware joint loss function to minimize the point-to-edge distances.”
• PointFlow: 3D Point Cloud Generation With Continuous Normalizing Flows (2019, background): “Getting more points for a particular shape requires separate up-sampling models such as [52, 51, 50].”
• Patch-Based Progressive 3D Point Set Upsampling (2018, methodology): “For sparse input though, EC-Net produces more artifacts, possibly because the geodesic KNN, which EC-Net is built upon, becomes unreliable under sparse inputs.”