# PointAtrousGraph: Deep Hierarchical Encoder-Decoder with Point Atrous Convolution for Unorganized 3D Points

arXiv: https://arxiv.org/abs/1907.09798 · HTML: https://mlsanity.com/paper/1907.09798/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Jul 2019.

## Built on by (most cited first, 2 of 2)

- [Variational Relational Point Completion Network](https://mlsanity.com/paper/2104.10154/) (2021)
- [Variational Relational Point Completion Network for Robust 3D Classification](https://mlsanity.com/paper/2304.09131/) (2023)

## Abstract (arXiv)

Motivated by the success of encoding multi-scale contextual information for image analysis, we propose our PointAtrousGraph (PAG) - a deep permutation-invariant hierarchical encoder-decoder for efficiently exploiting multi-scale edge features in point clouds. Our PAG is constructed by several novel modules, such as Point Atrous Convolution (PAC), Edge-preserved Pooling (EP) and Edge-preserved Unpooling (EU). Similar with atrous convolution, our PAC can effectively enlarge receptive fields of filters and thus densely learn multi-scale point features. Following the idea of non-overlapping max-pooling operations, we propose our EP to preserve critical edge features during subsampling. Correspondingly, our EU modules gradually recover spatial information for edge features. In addition, we introduce chained skip subsampling/upsampling modules that directly propagate edge features to the final stage. Particularly, our proposed auxiliary loss functions can further improve our performance. Experimental results show that our PAG outperform previous state-of-the-art methods on various 3D semantic perception applications.