Point transformer
Engel N, Dietmayer K, Belagiannis V (2021)
Publication Type: Journal article
Publication year: 2021
Journal
Book Volume: 9
Pages Range: 134826-134840
DOI: 10.1109/ACCESS.2021.3116304
Abstract
In this work, we present Point Transformer, a deep neural network that operates directly on unordered and unstructured point sets. We design Point Transformer to extract local and global features and relate both representations by introducing the local-global attention mechanism, which aims to capture spatial point relations and shape information. For that purpose, we propose SortNet, as part of the Point Transformer, which induces input permutation invariance by selecting points based on a learned score. The output of Point Transformer is a sorted and permutation invariant feature list that can directly be incorporated into common computer vision applications. We evaluate our approach on standard classification and part segmentation benchmarks to demonstrate competitive results compared to the prior work.
Authors with CRIS profile
Involved external institutions
Germany (DE)How to cite
APA:
Engel, N., Dietmayer, K., & Belagiannis, V. (2021). Point transformer. IEEE Access, 9, 134826-134840. https://dx.doi.org/10.1109/ACCESS.2021.3116304
MLA:
Engel, Nico, Klaus Dietmayer, and Vasileios Belagiannis. "Point transformer." IEEE Access 9 (2021): 134826-134840.
BibTeX: Download