CSDN: Cross-Modal Shape-Transfer Dual-Refinement Network for Point Cloud Completion

Zhe Zhu, Liangliang Nan, Haoran Xie, Honghua Chen, Jun Wang, Mingqiang Wei, Jing Qin

Research output: Contribution to journalArticleScientificpeer-review

Abstract

How will you repair a physical object with some missings? You may imagine its original shape from previously captured images, recover its overall (global) but coarse shape first, and then refine its local details. We are motivated to imitate the physical repair procedure to address point cloud completion. To this end, we propose a cross-modal shape-transfer dual-refinement network (termed CSDN), a coarse-to-fine paradigm with images of full-cycle participation, for quality point cloud completion. CSDN mainly consists of &#x201C;shape fusion&#x201D; and &#x201C;dual-refinement&#x201D; modules to tackle the cross-modal challenge. The first module transfers the intrinsic shape characteristics from single images to guide the geometry generation of the missing regions of point clouds, in which we propose IPAdaIN to embed the global features of both the image and the partial point cloud into completion. The second module refines the coarse output by adjusting the positions of the generated points, where the local refinement unit exploits the geometric relation between the novel and the input points by graph convolution, and the global constraint unit utilizes the input image to fine-tune the generated offset. Different from most existing approaches, CSDN not only explores the complementary information from images but also effectively exploits cross-modal data in the <italic>whole</italic> coarse-to-fine completion procedure. Experimental results indicate that CSDN performs favorably against twelve competitors on the cross-modal benchmark.

Original languageEnglish
Pages (from-to)1-18
Number of pages18
JournalIEEE Transactions on Visualization and Computer Graphics
DOIs
Publication statusSubmitted - 2023

Bibliographical note

Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care
Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

Keywords

  • cross modality
  • CSDN
  • Fuses
  • Geometry
  • Maintenance engineering
  • multi-feature fusion
  • point cloud completion
  • Point cloud compression
  • Shape
  • Three-dimensional displays
  • Transformers

Fingerprint

Dive into the research topics of 'CSDN: Cross-Modal Shape-Transfer Dual-Refinement Network for Point Cloud Completion'. Together they form a unique fingerprint.

Cite this