Abstract
How will you repair a physical object with large missings? You may first recover its global yet coarse shape and stepwise increase its local details. We are motivated to imitate the above physical repair procedure to address the point cloud completion task. We propose a novel stepwise point cloud completion network (SPCNet) for various 3D models with large missings. SPCNet has a hierarchical bottom-to-up network architecture. It fulfills shape completion in an iterative manner, which 1) first infers the global feature of the coarse result; 2) then infers the local feature with the aid of global feature; and 3) finally infers the detailed result with the help of local feature and coarse result. Beyond the wisdom of simulating the physical repair, we newly design a cycle loss to enhance the generalization and robustness of SPCNet. Extensive experiments clearly show the superiority of our SPCNet over the state-of-the-art methods on 3D point clouds with large missings. Code is available at https://github.com/1127368546/SPCNet.
| Original language | English |
|---|---|
| Pages (from-to) | 153-164 |
| Number of pages | 12 |
| Journal | Computer Graphics Forum |
| Volume | 41 |
| Issue number | 7 |
| DOIs | |
| Publication status | Published - Oct 2022 |
| Externally published | Yes |
Bibliographical note
Publisher Copyright:© 2022 The Author(s) Computer Graphics Forum © 2022 The Eurographics Association and John Wiley & Sons Ltd. Published by John Wiley & Sons Ltd.
Funding
This work was supported by the National Natural Science Foundation of China (No. 62172218, No. 62032011), the Free Exploration of Basic Research Project, Local Science and Technology Development Fund Guided by the Central Government of China (No. 2021Szvup060), and the Natural Science Foundation of Guangdong Province (No. 2022A1515010170), and a grant from the Research Grants Council of the Hong Kong Special Administrative Region, China (No. UGC/FDS16/E14/21).