Self-Sampling for Neural Point Cloud Consolidation
- 24 September 2021
- journal article
- research article
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 40 (5), 1-14
- https://doi.org/10.1145/3470645
Abstract
We introduce a novel technique for neural point cloud consolidation which learns from only the input point cloud. Unlike other point up-sampling methods which analyze shapes via local patches, in this work, we learn from global subsets. We repeatedly self-sample the input point cloud with global subsets that are used to train a deep neural network. Specifically, we define source and target subsets according to the desired consolidation criteria (e.g., generating sharp points or points in sparse regions). The network learns a mapping from source to target subsets, and implicitly learns to consolidate the point cloud. During inference, the network is fed with random subsets of points from the input, which it displaces to synthesize a consolidated point set. We leverage the inductive bias of neural networks to eliminate noise and outliers, a notoriously difficult problem in point cloud consolidation. The shared weights of the network are optimized over the entire shape, learning non-local statistics and exploiting the recurrence of local-scale geometries. Specifically, the network encodes the distribution of the underlying shape surface within a fixed set of local kernels, which results in the best explanation of the underlying shape surface. We demonstrate the ability to consolidate point sets from a variety of shapes, while eliminating outliers and noise.Keywords
This publication has 29 references indexed in Scilit:
- A Survey of Surface Reconstruction from Point CloudsComputer Graphics Forum, 2016
- Robust surface reconstruction via dictionary learningACM Transactions on Graphics, 2014
- L 1 -medial skeleton of point cloudACM Transactions on Graphics, 2013
- A benchmark for surface reconstructionACM Transactions on Graphics, 2013
- Edge-aware point set resamplingACM Transactions on Graphics, 2013
- Consolidation of unorganized point clouds for surface reconstructionACM Transactions on Graphics, 2009
- Parameterization-free projection for geometry reconstructionACM Transactions on Graphics, 2007
- Parameterization-free projection for geometry reconstructionACM Transactions on Graphics, 2007
- Fast and Effective Feature-Preserving Mesh DenoisingIEEE Transactions on Visualization and Computer Graphics, 2007
- The ball-pivoting algorithm for surface reconstructionIEEE Transactions on Visualization and Computer Graphics, 1999