{"type":"ScholarlyArticle","title":"PointLIE: Locally Invertible Embedding for Point Cloud Sampling and Recovery","authors":[{"name":"Weibing Zhao","slug":"weibing-zhao","given":"Weibing","family":"Zhao","affiliation":""},{"name":"Xu Yan","slug":"xu-yan","given":"Xu","family":"Yan","affiliation":""},{"name":"Jiantao Gao","slug":"jiantao-gao","given":"Jiantao","family":"Gao","affiliation":""},{"name":"Ruimao Zhang","slug":"ruimao-zhang","given":"Ruimao","family":"Zhang","affiliation":""},{"name":"Jiayan Zhang","slug":"jiayan-zhang","given":"Jiayan","family":"Zhang","affiliation":""},{"name":"Zhen Li","slug":"zhen-li","given":"Zhen","family":"Li","affiliation":""},{"name":"Song Wu","slug":"song-wu","given":"Song","family":"Wu","affiliation":""},{"name":"Shuguang Cui","slug":"shuguang-cui","given":"Shuguang","family":"Cui","affiliation":""}],"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.","doi":"10.24963/ijcai.2021/186","url":"https://ijcai.org/proceedings/2021/186","pdf":"https://ijcai.org/proceedings/2021/0186.pdf","markdown":"https://ijcai.org/proceedings/2021/186.md","bibtex":"https://ijcai.org/proceedings/2021/bibtex/186","volume":{"slug":"2021","title":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2021","url":"https://ijcai.org/proceedings/2021/","year":2021,"location":"Montreal","dates":"19-27 August 2021","editors":"Prof. Zhi-Hua Zhou","isbn":"978-0-9992411-9-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2021"},"section":"Computer Vision II","track":"Main Track","number":186,"pages":{"first":1345,"last":1351},"keywords":["Computer Vision: 2D and 3D Computer Vision","Machine Learning: Deep Learning"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}