Neighborhood-based neural implicit reconstruction from point clouds

Haiyong Jiang, Jianfei Cai, Jianmin Zheng, Jun Xiao

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

1 Citation (Scopus)

Abstract

Neural implicit reconstruction is emerging as a promising approach to constructing 3D geometry from point clouds due to its ability to model geometry with complicated topology and unrestricted resolution. Current methods in this category usually deliver smooth and good quality results,but suffer from defective details and generalization issues. The major reason is that these methods use either a global code or interpolated feature on 3D grids of limited resolution to estimate implicit surface,therefore may cause distortion in feature discretization. This paper presents a neighborhood-aware neural implicit reconstruction framework that consists of an encoder network,a feature aggregation module,and a decoder network to learn implicit surface. The method can easily incorporate an off-the-shelf 3D point-based or volume-based neural network as an encoder. At the heart of our framework is the aggregation module that fuses the learnt contextual features on neighbor inputs so that the method can directly exploit local features of neighboring inputs for geometry detail recovery as well as cross-domain generalization. Experimental results demonstrate that our method significantly outperforms the state-of-the-art methods (about 4.0 points IoU improvements in ShapeNet dataset and 9.0 points IoU improvements in DFAUST dataset). Furthermore,our method preserves finer shape details and can be successfully transferred to a novel category without fine-tuning.

Original languageEnglish
Title of host publicationProceedings - 2021 International Conference on 3D Vision, 3DV 2021
EditorsJean-Yves Guillemaut, Armin Mustafa
Place of PublicationPiscataway NJ USA
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages1259-1268
Number of pages10
ISBN (Electronic)9781665426886
ISBN (Print)9781665426893
DOIs
Publication statusPublished - 2021
EventInternational Conference on 3D Vision 2021 - Online, United Kingdom
Duration: 1 Dec 20213 Dec 2021
Conference number: 9th
https://ieeexplore.ieee.org/xpl/conhome/9665713/proceeding (Proceedings)

Publication series

NameProceedings - 2021 International Conference on 3D Vision, 3DV 2021
PublisherIEEE, Institute of Electrical and Electronics Engineers
ISSN (Print)2378-3826
ISSN (Electronic)2475-7888

Conference

ConferenceInternational Conference on 3D Vision 2021
Abbreviated title3DV 2021
Country/TerritoryUnited Kingdom
Period1/12/213/12/21
Internet address

Keywords

  • 3D reconstruction
  • Implicit surface
  • point cloud

Cite this