---
title: "PointLIE: Locally Invertible Embedding for Point Cloud Sampling and Recovery"
authors:
  - "Weibing Zhao"
  - "Xu Yan"
  - "Jiantao Gao"
  - "Ruimao Zhang"
  - "Jiayan Zhang"
  - "Zhen Li"
  - "Song Wu"
  - "Shuguang Cui"
doi: "10.24963/ijcai.2021/186"
url: "https://ijcai.org/proceedings/2021/186"
pdf: "https://ijcai.org/proceedings/2021/0186.pdf"
venue: "Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence"
year: 2021
pages: "1345-1351"
track: "Main Track"
keywords:
  - "Computer Vision: 2D and 3D Computer Vision"
  - "Machine Learning: Deep Learning"
---

# PointLIE: Locally Invertible Embedding for Point Cloud Sampling and Recovery

Weibing Zhao, Xu Yan, Jiantao Gao, Ruimao Zhang, Jiayan Zhang, Zhen Li, Song Wu, Shuguang Cui

*Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence*, pages 1345-1351. DOI: [10.24963/ijcai.2021/186](https://doi.org/10.24963/ijcai.2021/186)

## Abstract

Point Cloud Sampling and Recovery (PCSR) is critical for massive real-time point cloud collection and processing since raw data usually requires large storage and computation. This paper addresses a fundamental problem in PCSR: How to downsample the dense point cloud with arbitrary scales while preserving the local topology of discarded points in a case-agnostic manner (i.e., without additional storage for point relationships)? We propose a novel Locally Invertible Embedding (PointLIE) framework to unify the point cloud sampling and upsampling into one single framework through bi-directional learning. Specifically, PointLIE decouples the local geometric relationships between discarded points from the sampled points by progressively encoding the neighboring offsets to a latent variable. Once the latent variable is forced to obey a pre-defined distribution in the forward sampling path, the recovery can be achieved effectively through inverse operations. Taking the recover-pleasing sampled points and a latent embedding randomly drawn from the specified distribution as inputs, PointLIE can theoretically guarantee the fidelity of reconstruction and outperform state-of-the-arts quantitatively and qualitatively.