Hermosilla, P;
Ritschel, T;
Vázquez, P-P;
Vinacua, A;
Ropinski, T;
(2018)
Monte Carlo Convolution for Learning on Non-Uniformly Sampled Point Clouds.
ACM Transactions on Graphics
, 37
(6)
, Article 235. 10.1145/3272127.3275110.
Preview |
Text
hermosilla2018montecarlo.pdf - Published Version Download (17MB) | Preview |
Abstract
Deep learning systems extensively use convolution operations to process input data. Though convolution is clearly defined for structured data such as 2D images or 3D volumes, this is not true for other data types such as sparse point clouds. Previous techniques have developed approximations to convolutions for restricted conditions. Unfortunately, their applicability is limited and cannot be used for general point clouds. We propose an efficient and effective method to learn convolutions for non-uniformly sampled point clouds, as they are obtained with modern acquisition techniques. Learning is enabled by four key novelties: first, representing the convolution kernel itself as a multilayer perceptron; second, phrasing convolution as a Monte Carlo integration problem, third, using this notion to combine information from multiple samplings at different levels; and fourth using Poisson disk sampling as a scalable means of hierarchical point cloud learning. The key idea across all these contributions is to guarantee adequate consideration of the underlying non-uniform sample distribution function from a Monte Carlo perspective. To make the proposed concepts applicable to real-world tasks, we furthermore propose an efficient implementation which significantly reduces the GPU memory required during the training process. By employing our method in hierarchical network architectures we can outperform most of the state-of-the-art networks on established point cloud segmentation, classification and normal estimation benchmarks. Furthermore, in contrast to most existing approaches, we also demonstrate the robustness of our method with respect to sampling variations, even when training with uniformly sampled data only. To support the direct application of these concepts, we provide a ready-to-use TensorFlow implementation of these layers at https://github.com/viscom-ulm/MCCNN.
| Type: | Article |
|---|---|
| Title: | Monte Carlo Convolution for Learning on Non-Uniformly Sampled Point Clouds |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.1145/3272127.3275110 |
| Publisher version: | https://doi.org/10.1145/3272127.3275110 |
| Language: | English |
| Additional information: | This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions. |
| Keywords: | Deep learning; Convolutional neural networks; Point clouds; Monte Carlo integration |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10066112 |
Archive Staff Only
 |
View Item |
