Neural Implicit Embedding for Point Cloud Analysis
| Autor: | Taiichi Hashimoto, Kent Fujiwara |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Artificial neural network
Computer science business.industry Point cloud 020207 software engineering 02 engineering and technology 010501 environmental sciences 01 natural sciences Robustness (computer science) 0202 electrical engineering electronic engineering information engineering Embedding Segmentation Artificial intelligence business Distance transform Algorithm 0105 earth and related environmental sciences Extreme learning machine |
| Zdroj: | CVPR |
| DOI: | 10.1109/cvpr42600.2020.01175 |
| Popis: | We present a novel representation for point clouds that encapsulates the local characteristics of the underlying structure. The key idea is to embed an implicit representation of the point cloud, namely the distance field, into neural networks. One neural network is used to embed a portion of the distance field around a point. The resulting network weights are concatenated to be used as a representation of the corresponding point cloud instance. To enable comparison among the weights, Extreme Learning Machine (ELM) is employed as the embedding network. Invariance to scale and coordinate change can be achieved by introducing a scale commutative activation layer to the ELM, and aligning the distance field into a canonical pose. Experimental results using our representation demonstrate that our proposal is capable of similar or better classification and segmentation performance compared to the state-of-the-art point-based methods, while requiring less time for training. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|