Deep points consolidation

By Shihao Wu, Hui Huang, Minglun Gong, Matthias Zwicker, Daniel Cohen-Or. 2015

138 citations recorded by the source corpus.

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

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. Kang Yin

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. Kang Yin

Citations in the corpus

• PointCNN: Convolution On X-Transformed Points (2018, background): “We suspect some more advanced point selections which have shown promising performance in geometry processing, such as Deep Points [51], could fit in here as well.”
• P2P-NET: Bidirectional Point Displacement Net for Shape Transform (methodology): “We use the chair and airplane datasets of ModelNet40 [Wu et al. 2015b] With the synthesized surface samples, meso-skeletons, and single-view point scans, we tested our method on three pairs of transformations among the three different types of point sets, i.e., meso-skeleton vs. surface,…”
• PU-Net: Point Cloud Upsampling Network (2018, methodology): “It is worth mentioning that Wu et al. [29] propose a deep points representation method to fuse consolidation and completion into one coherent step.”
• Patch-Based Progressive 3D Point Set Upsampling (2018, methodology): “[53] fill points in large areas of missing data by jointly optimizing both the surface and the inner points, using the extracted meso-skeleton to guide the surface point set resampling.”
• High-Resolution Shape Completion Using Deep Neural Networks for Global Structure and Local Geometry Inference (2017, background): “By assuming local surface or volumetric smoothness, a number of geometry-based methods ([12] [26] [30]) can successfully recover the underlying surface in the case of small gaps.”
• PU-GAN: A Point Cloud Upsampling Adversarial Network (2019, methodology): “[33] proposed a consolidation method to fill large holes and complete missing regions by introducing a new deep point representation.”