Recurrent Multi-view Alignment Network for Unsupervised Surface Registration

Research output: Chapters, Conference Papers, Creative and Literary Works (RGC: 12, 32, 41, 45)32_Refereed conference paper (with ISBN/ISSN)peer-review

View graph of relations

Author(s)

  • Wanquan Feng
  • Juyong Zhang
  • Hongrui Cai
  • Haofei Xu
  • Hujun Bao

Related Research Unit(s)

Detail(s)

Original languageEnglish
Title of host publicationProceedings - 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition
Subtitle of host publicationCVPR 2021
PublisherIEEE
Pages10292-10302
ISBN (Electronic)9781665445092
ISBN (Print)9781665445108
Publication statusPublished - 2021

Publication series

Name
ISSN (Print)1063-6919
ISSN (Electronic)2575-7075

Conference

Title2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2021)
LocationVirtual
Period19 - 25 June 2021

Abstract

Learning non-rigid registration in an end-to-end manner is challenging due to the inherent high degrees of freedom and the lack of labeled training data. In this paper, we resolve these two challenges simultaneously. First, we propose to represent the non-rigid transformation with a point-wise combination of several rigid transformations. This representation not only makes the solution space well-constrained but also enables our method to be solved iteratively with a recurrent framework, which greatly reduces the difficulty of learning. Second, we introduce a differentiable loss function that measures the 3D shape similarity on the projected multi-view 2D depth images so that our full framework can be trained end-to-end without ground truth supervision. Extensive experiments on several different datasets demonstrate that our proposed method outperforms the previous state-of-the-art by a large margin. The source codes are available at https://github.com/WanquanF/RMA-Net.

Research Area(s)

  • cs.CV, cs.GR

Bibliographic Note

Research Unit(s) information for this publication is provided by the author(s) concerned.

Citation Format(s)

Recurrent Multi-view Alignment Network for Unsupervised Surface Registration. / Feng, Wanquan; Zhang, Juyong; Cai, Hongrui; Xu, Haofei; Hou, Junhui; Bao, Hujun.

Proceedings - 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition: CVPR 2021. IEEE, 2021. p. 10292-10302.

Research output: Chapters, Conference Papers, Creative and Literary Works (RGC: 12, 32, 41, 45)32_Refereed conference paper (with ISBN/ISSN)peer-review