Skip to main navigation Skip to search Skip to main content

VMNet: Voxel-Mesh Network for Geodesic-Aware 3D Semantic Segmentation

  • Zeyu Hu
  • , Xuyang Bai
  • , Jiaxiang Shang
  • , Runze Zhang
  • , Jiayu Dong
  • , Xin Wang
  • , Guangyuan Sun
  • , Hongbo Fu*
  • , Chiew-Lan Tai
  • *Corresponding author for this work

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

Abstract

In recent years, sparse voxel-based methods have become the state-of-the-arts for 3D semantic segmentation of indoor scenes, thanks to the powerful 3D CNNs. Nevertheless, being oblivious to the underlying geometry, voxel-based methods suffer from ambiguous features on spatially close objects and struggle with handling complex and irregular geometries due to the lack of geodesic information. In view of this, we present Voxel-Mesh Network (VMNet), a novel 3D deep architecture that operates on the voxel and mesh representations leveraging both the Euclidean and geodesic information. Intuitively, the Euclidean information extracted from voxels can offer contextual cues representing interactions between nearby objects, while the geodesic information extracted from meshes can help separate objects that are spatially close but have disconnected surfaces. To incorporate such information from the two domains, we design an intra-domain attentive module for effective feature aggregation and an inter-domain attentive module for adaptive feature fusion. Experimental results validate the effectiveness of VMNet: specifically, on the challenging ScanNet dataset for large-scale segmentation of indoor scenes, it outperforms the state-of-the-art SparseConvNet and MinkowskiNet (74.6% vs 72.5% and 73.6% in mIoU) with a simpler network structure (17M vs 30M and 38M parameters). Code release: https://github.com/hzykent/VMNet.
Original languageEnglish
Title of host publicationProceedings - 2021 IEEE/CVF International Conference on Computer Vision (ICCV 2021)
PublisherIEEE
Pages15468-15474
ISBN (Electronic)978-1-6654-2812-5
DOIs
Publication statusPublished - Oct 2021
Event18th IEEE/CVF International Conference on Computer Vision, ICCV 2021 - Virtual, Online, Canada
Duration: 11 Oct 202117 Oct 2021

Publication series

NameProceedings of the IEEE International Conference on Computer Vision
ISSN (Print)1550-5499

Conference

Conference18th IEEE/CVF International Conference on Computer Vision, ICCV 2021
PlaceCanada
CityVirtual, Online
Period11/10/2117/10/21

Bibliographical note

Full text of this publication does not contain sufficient affiliation information. With consent from the author(s) concerned, the Research Unit(s) information for this record is based on the existing academic department affiliation of the author(s).

Fingerprint

Dive into the research topics of 'VMNet: Voxel-Mesh Network for Geodesic-Aware 3D Semantic Segmentation'. Together they form a unique fingerprint.

Cite this