Reproducibility Companion Paper: Campus3D: A Photogrammetry Point Cloud Benchmark for Outdoor Scene Hierarchical Understanding

Yuqing Liao; Xinke Li; Zekun Tong; Yabang Zhao; Andrew Lim; Zhenzhong Kuang; Cise Midoglu

doi:10.1145/3474085.3477934

Reproducibility Companion Paper: Campus3D: A Photogrammetry Point Cloud Benchmark for Outdoor Scene Hierarchical Understanding

Yuqing Liao
, Xinke Li
, Zekun Tong
, Yabang Zhao
, Andrew Lim
, Zhenzhong Kuang
, Cise Midoglu

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

25 Downloads (CityUHK Scholars)

Abstract

This companion paper is to support the replication of paper "Campus3D: A Photogrammetry Point Cloud Benchmark for Outdoor Scene Hierarchical Understanding", which was presented at ACM Multimedia 2020. The supported paper's main purpose was to provide a photogrammetry point cloud-based dataset with hierarchical multilabels to facilitate the area of 3D deep learning. Based on this provided dataset and source code, in this work, we build a complete package to reimplement the proposed methods and experiments (i.e., the hierarchical learning framework and the benchmarks of the hierarchical semantic segmentation task). Specifically, this paper contains the technical details of the package, including file structure, dataset preparation, installation package, and the conduction of the experiment. We also present the replicated experiment results and indicate our contributions to the original implementation. © 2021 Copyright held by the owner/author(s).

Original language	English
Title of host publication	MM ’21
Subtitle of host publication	Proceedings of the 29th ACM International Conference on Multimedia
Publisher	Association for Computing Machinery
Pages	3610-3614
ISBN (Print)	9781450386517
DOIs	https://doi.org/10.1145/3474085.3477934
Publication status	Published - 2021
Externally published	Yes
Event	29th ACM International Conference on Multimedia (MM 2021) - Hybrid, Chengdu, China Duration: 20 Oct 2021 → 24 Oct 2021 https://2021.acmmm.org/

Publication series

Name	MM - Proceedings of the ACM International Conference on Multimedia

Conference

Conference	29th ACM International Conference on Multimedia (MM 2021)
Abbreviated title	MM '21
Place	China
City	Chengdu
Period	20/10/21 → 24/10/21
Internet address	https://2021.acmmm.org/

Research Keywords

dataset
hierarchical learning
instance segmentation
point cloud
reproducibility
scene understanding
semantic segmentation

Publisher's Copyright Statement

This full text is made available under CC-BY 4.0. https://creativecommons.org/licenses/by/4.0/

Access Output

10.1145/3474085.3477934

231903135.pdfFinal Published version, 1.32 MBLicence: CC BY

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

Liao, Y., Li, X., Tong, Z., Zhao, Y., Lim, A., Kuang, Z., & Midoglu, C. (2021). Reproducibility Companion Paper: Campus3D: A Photogrammetry Point Cloud Benchmark for Outdoor Scene Hierarchical Understanding. In MM ’21: Proceedings of the 29th ACM International Conference on Multimedia (pp. 3610-3614). (MM - Proceedings of the ACM International Conference on Multimedia). Association for Computing Machinery. https://doi.org/10.1145/3474085.3477934

Liao, Yuqing ; Li, Xinke ; Tong, Zekun et al. / Reproducibility Companion Paper: Campus3D : A Photogrammetry Point Cloud Benchmark for Outdoor Scene Hierarchical Understanding. MM ’21: Proceedings of the 29th ACM International Conference on Multimedia. Association for Computing Machinery, 2021. pp. 3610-3614 (MM - Proceedings of the ACM International Conference on Multimedia).

@inproceedings{fe00d1b9293a47fba51764adb427d14a,

title = "Reproducibility Companion Paper: Campus3D: A Photogrammetry Point Cloud Benchmark for Outdoor Scene Hierarchical Understanding",

abstract = "This companion paper is to support the replication of paper {"}Campus3D: A Photogrammetry Point Cloud Benchmark for Outdoor Scene Hierarchical Understanding{"}, which was presented at ACM Multimedia 2020. The supported paper's main purpose was to provide a photogrammetry point cloud-based dataset with hierarchical multilabels to facilitate the area of 3D deep learning. Based on this provided dataset and source code, in this work, we build a complete package to reimplement the proposed methods and experiments (i.e., the hierarchical learning framework and the benchmarks of the hierarchical semantic segmentation task). Specifically, this paper contains the technical details of the package, including file structure, dataset preparation, installation package, and the conduction of the experiment. We also present the replicated experiment results and indicate our contributions to the original implementation. {\textcopyright} 2021 Copyright held by the owner/author(s).",

keywords = "dataset, hierarchical learning, instance segmentation, point cloud, reproducibility, scene understanding, semantic segmentation",

author = "Yuqing Liao and Xinke Li and Zekun Tong and Yabang Zhao and Andrew Lim and Zhenzhong Kuang and Cise Midoglu",

year = "2021",

doi = "10.1145/3474085.3477934",

language = "English",

isbn = "9781450386517",

series = "MM - Proceedings of the ACM International Conference on Multimedia",

publisher = "Association for Computing Machinery",

pages = "3610--3614",

booktitle = "MM {\textquoteright}21",

address = "United States",

note = "29th ACM International Conference on Multimedia (MM 2021), MM '21 ; Conference date: 20-10-2021 Through 24-10-2021",

url = "https://2021.acmmm.org/",

}

Liao, Y, Li, X, Tong, Z, Zhao, Y, Lim, A, Kuang, Z & Midoglu, C 2021, Reproducibility Companion Paper: Campus3D: A Photogrammetry Point Cloud Benchmark for Outdoor Scene Hierarchical Understanding. in MM ’21: Proceedings of the 29th ACM International Conference on Multimedia. MM - Proceedings of the ACM International Conference on Multimedia, Association for Computing Machinery, pp. 3610-3614, 29th ACM International Conference on Multimedia (MM 2021), Chengdu, China, 20/10/21. https://doi.org/10.1145/3474085.3477934

Reproducibility Companion Paper: Campus3D: A Photogrammetry Point Cloud Benchmark for Outdoor Scene Hierarchical Understanding. / Liao, Yuqing; Li, Xinke; Tong, Zekun et al.
MM ’21: Proceedings of the 29th ACM International Conference on Multimedia. Association for Computing Machinery, 2021. p. 3610-3614 (MM - Proceedings of the ACM International Conference on Multimedia).

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - Reproducibility Companion Paper: Campus3D

T2 - 29th ACM International Conference on Multimedia (MM 2021)

AU - Liao, Yuqing

AU - Li, Xinke

AU - Tong, Zekun

AU - Zhao, Yabang

AU - Lim, Andrew

AU - Kuang, Zhenzhong

AU - Midoglu, Cise

PY - 2021

Y1 - 2021

N2 - This companion paper is to support the replication of paper "Campus3D: A Photogrammetry Point Cloud Benchmark for Outdoor Scene Hierarchical Understanding", which was presented at ACM Multimedia 2020. The supported paper's main purpose was to provide a photogrammetry point cloud-based dataset with hierarchical multilabels to facilitate the area of 3D deep learning. Based on this provided dataset and source code, in this work, we build a complete package to reimplement the proposed methods and experiments (i.e., the hierarchical learning framework and the benchmarks of the hierarchical semantic segmentation task). Specifically, this paper contains the technical details of the package, including file structure, dataset preparation, installation package, and the conduction of the experiment. We also present the replicated experiment results and indicate our contributions to the original implementation. © 2021 Copyright held by the owner/author(s).

AB - This companion paper is to support the replication of paper "Campus3D: A Photogrammetry Point Cloud Benchmark for Outdoor Scene Hierarchical Understanding", which was presented at ACM Multimedia 2020. The supported paper's main purpose was to provide a photogrammetry point cloud-based dataset with hierarchical multilabels to facilitate the area of 3D deep learning. Based on this provided dataset and source code, in this work, we build a complete package to reimplement the proposed methods and experiments (i.e., the hierarchical learning framework and the benchmarks of the hierarchical semantic segmentation task). Specifically, this paper contains the technical details of the package, including file structure, dataset preparation, installation package, and the conduction of the experiment. We also present the replicated experiment results and indicate our contributions to the original implementation. © 2021 Copyright held by the owner/author(s).

KW - dataset

KW - hierarchical learning

KW - instance segmentation

KW - point cloud

KW - reproducibility

KW - scene understanding

KW - semantic segmentation

UR - https://www.scopus.com/pages/publications/85119336703

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85119336703&origin=recordpage

U2 - 10.1145/3474085.3477934

DO - 10.1145/3474085.3477934

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 9781450386517

T3 - MM - Proceedings of the ACM International Conference on Multimedia

SP - 3610

EP - 3614

BT - MM ’21

PB - Association for Computing Machinery

Y2 - 20 October 2021 through 24 October 2021

ER -

Liao Y, Li X, Tong Z, Zhao Y, Lim A, Kuang Z et al. Reproducibility Companion Paper: Campus3D: A Photogrammetry Point Cloud Benchmark for Outdoor Scene Hierarchical Understanding. In MM ’21: Proceedings of the 29th ACM International Conference on Multimedia. Association for Computing Machinery. 2021. p. 3610-3614. (MM - Proceedings of the ACM International Conference on Multimedia). Epub 2021 Oct 17. doi: 10.1145/3474085.3477934

Reproducibility Companion Paper: Campus3D: A Photogrammetry Point Cloud Benchmark for Outdoor Scene Hierarchical Understanding

Abstract

Publication series

Conference

Research Keywords

Publisher's Copyright Statement

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this