2021 IEEE International Conference on Image Processing

19-22 September 2021 • Anchorage, Alaska, USA

Imaging Without Borders

2021 IEEE International Conference on Image Processing

19-22 September 2021 • Anchorage, Alaska, USA

Login Paper Search My Schedule Paper Index Help

My ICIP 2021 Schedule

Note: Your custom schedule will not be saved unless you create a new account or login to an existing account.
  1. Create a login based on your email (takes less than one minute)
  2. Perform 'Paper Search'
  3. Select papers that you desire to save in your personalized schedule
  4. Click on 'My Schedule' to see the current list of selected papers
  5. Click on 'Printable Version' to create a separate window suitable for printing (the header and menu will appear, but will not actually print)

Paper Detail

Paper IDSS-3DPU.3
Paper Title 3D GRID TRANSFORMATION NETWORK FOR POINT CLOUD COMPLETION
Authors Xiaobao Deng, Xiaolin Hu, Nicholas Buris, Ping An, Yilei Chen, Shanghai University, China
SessionSS-3DPU: Special Session: 3D Visual Perception and Understanding
LocationArea B
Session Time:Tuesday, 21 September, 15:30 - 17:00
Presentation Time:Tuesday, 21 September, 15:30 - 17:00
Presentation Poster
Topic Special Sessions: 3D Visual Perception and Understanding
IEEE Xplore Open Preview  Click here to view in IEEE Xplore
Abstract Point cloud completion plays an important role in 3D scene modeling because point clouds collected from sensors tend to be sparse and incomplete. Existing methods prefer to transform 2D grid points to the underlying surface of output point clouds. However, the point clouds they complete commonly retain the original plane structure and fail to recover details. To solve the problem, we propose 3D Grid Transformation Network. Unlike transforming 3D grid points to point clouds directly, we calculate their weights for the reconstructed point clouds. Our method can break the topology of the 3D grid structure and makes the underlying shape of output point clouds closer to the ground truth. We validate our method on point cloud completion and experimental results show that our method can achieve better quantitative results and obtain fine-grained details.