Learning Part Boundaries from 3D Point Clouds
arXiv:2007.07563 · doi:10.1111/cgf.14078
Abstract
We present a method that detects boundaries of parts in 3D shapes represented as point clouds. Our method is based on a graph convolutional network architecture that outputs a probability for a point to lie in an area that separates two or more parts in a 3D shape. Our boundary detector is quite generic: it can be trained to localize boundaries of semantic parts or geometric primitives commonly used in 3D modeling. Our experiments demonstrate that our method can extract more accurate boundaries that are closer to ground-truth ones compared to alternatives. We also demonstrate an application of our network to fine-grained semantic shape segmentation, where we also show improvements in terms of part labeling performance.
Appeared in Eurographics Symposium on Geometry Processing 2020
References in corpus (13)
- Adam: A Method for Stochastic Optimization
- Geometric deep learning: going beyond Euclidean data
- O-CNN: Octree-based Convolutional Neural Networks for 3D Shape Analysis
- Point-Voxel CNN for Efficient 3D Deep Learning
- Supervised Fitting of Geometric Primitives to 3D Point Clouds
- Monte Carlo Convolution for Learning on Non-Uniformly Sampled Point Clouds
- Adaptive O-CNN: A Patch-based Deep Representation of 3D Shapes
- Deep Crisp Boundaries: From Boundaries to Higher-level Tasks
- Semantic Edge Detection with Diverse Deep Supervision
- Geometric Capsule Autoencoders for 3D Point Clouds
- Three Birds One Stone: A General Architecture for Salient Object Segmentation, Edge Detection and Skeleton Extraction
- Unsupervised Feature Learning for Point Cloud by Contrasting and Clustering With Graph Convolutional Neural Network
- RED-NET: A Recursive Encoder-Decoder Network for Edge Detection
Cited by in corpus (7)
- RFEPS: Reconstructing Feature-line Equipped Polygonal Surface
- PIG-Net: Inception based Deep Learning Architecture for 3D Point Cloud Segmentation
- Task-Aware Sampling Layer for Point-Wise Analysis
- EdgeFormer: local patch-based edge detection transformer on point clouds
- Random Walk on Point Clouds for Feature Detection
- One Shot Learning for Edge Detection on Point Clouds
- GAMesh: Guided and Augmented Meshing for Deep Point Networks