Unsupervised Learning of Intrinsic Structural Representation Points
arXiv:2003.01661
Abstract
Learning structures of 3D shapes is a fundamental problem in the field of computer graphics and geometry processing. We present a simple yet interpretable unsupervised method for learning a new structural representation in the form of 3D structure points. The 3D structure points produced by our method encode the shape structure intrinsically and exhibit semantic consistency across all the shape instances with similar structures. This is a challenging goal that has not fully been achieved by other methods. Specifically, our method takes a 3D point cloud as input and encodes it as a set of local features. The local features are then passed through a novel point integration module to produce a set of 3D structure points. The chamfer distance is used as reconstruction loss to ensure the structure points lie close to the input point cloud. Extensive experiments have shown that our method outperforms the state-of-the-art on the semantic shape correspondence task and achieves comparable performance with the state-of-the-art on the segmentation label transfer task. Moreover, the PCA based shape embedding built upon consistent structure points demonstrates good performance in preserving the shape structures. Code is available at https://github.com/NolenChen/3DStructurePoints
Accepted by CVPR 2020
References in corpus (9)
- Adam: A Method for Stochastic Optimization
- ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes
- Dynamic Graph CNN for Learning on Point Clouds
- Supervised Fitting of Geometric Primitives to 3D Point Clouds
- Learning Efficient Point Cloud Generation for Dense 3D Object Reconstruction
- Discovery of Latent 3D Keypoints via End-to-end Geometric Reasoning
- 3DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructions
- Learning elementary structures for 3D shape generation and matching
- AdaCoSeg: Adaptive Shape Co-Segmentation with Group Consistency Loss