Abstract | ||
---|---|---|
We present a method for discovering never-seen-before objects in 3D point clouds obtained from sensors like Microsoft Kinect. We generate supervoxels directly from the point cloud data and use them with a Siamese network, built on a recently proposed 3D convolutional neural network architecture. We use known objects to train a non-linear embedding of supervoxels, by optimizing the criteria that supervoxels which fall on the same object should be closer than those which fall on different objects, in the embedding space. We test on unknown objects, which were not seen during training, and perform clustering in the learned embedding space of supervoxels to effectively perform novel object discovery. We validate the method with extensive experiments, quantitatively showing that it can discover numerous unseen objects while being trained on only a few dense 3D models. We also show very good qualitative results of object discovery in point cloud data when the test objects, either specific instances or even categories, were never seen during training. |
Year | DOI | Venue |
---|---|---|
2018 | 10.1109/WACV.2018.00026 | 2018 IEEE Winter Conference on Applications of Computer Vision (WACV) |
Keywords | DocType | Volume |
learned embedding space,numerous unseen objects,dense 3D models,3D point clouds,Microsoft Kinect,Siamese network,nonlinear embedding,3D convolutional neural network architecture | Conference | abs/1701.07046 |
ISSN | ISBN | Citations |
2472-6737 | 978-1-5386-4887-2 | 1 |
PageRank | References | Authors |
0.34 | 43 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Siddharth Srivastava | 1 | 9 | 5.89 |
Gaurav Sharma | 2 | 391 | 15.11 |
Brejesh Lall | 3 | 85 | 43.42 |