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 ID3D-2.9
Paper Title SPHERERPN: LEARNING SPHERES FOR HIGH-QUALITY REGION PROPOSALS ON 3D POINT CLOUDS OBJECT DETECTION
Authors Thang Vu, Kookhoi Kim, Haeyong Kang, Xuan Thanh Nguyen, Tung M. Luu, Chang D. Yoo, Korea Advanced Institute of Science and Technology, Republic of Korea
Session3D-2: Point Cloud Processing 2
LocationArea J
Session Time:Wednesday, 22 September, 08:00 - 09:30
Presentation Time:Wednesday, 22 September, 08:00 - 09:30
Presentation Poster
Topic Three-Dimensional Image and Video Processing: Point cloud processing
IEEE Xplore Open Preview  Click here to view in IEEE Xplore
Abstract In 2D object detection, a bounding box commonly serves as the proxy for detecting an object. However, extending the bounding box to 3D detection makes the accuracy sensitive to localization error. This problem is more severe on flat objects since little localization error may lead to low overlaps between prediction and ground truth. To address this problem, this paper proposes Sphere Region Proposal Network (SphereRPN) which detects objects by learning spheres as opposed to bounding boxes. We demonstrate that spherical proposals are more robust to localization error compared to bounding box proposals. The proposed SphereRPN is not only accurate but also fast. Experiment results on the standard ScanNet dataset show that the proposed SphereRPN outperforms the previous state-of-the-art methods by a large margin while being 2x to 7x faster. The code will be made publicly available.