Learning Hierarchical Shape Segmentation and Labeling from Online Repositories
Authors:
Preprint
Abstract
We propose a method for converting geometric shapes into hierarchically segmented parts with part labels. Our key idea is to train category-specific models from the scene graphs and part names that accompany 3D shapes in public repositories. These freely-available annotations represent an enormous, untapped source of information on geometry. However, because the models and corresponding scene graphs are created by a wide range of modelers with different levels of expertise, modeling tools, and objectives, these models have very inconsistent segmentations and hierarchies with sparse and noisy textual tags. Our method involves two analysis steps. First, we perform a joint optimization to simultaneously cluster and label parts in the database while also inferring a canonical tag dictionary and part hierarchy. We then use this labeled data to train a method for hierarchical segmentation and labeling of new 3D shapes. We demonstrate that our method can mine complex information, detecting hierarchies in man-made objects and their constituent parts, obtaining finer scale details than existing alternatives. We also show that, by performing domain transfer using a few supervised examples, our technique outperforms fully-supervised techniques that require hundreds of manually-labeled models.Keywords
All Related Versions
- Version 1, 2017-05-04, ArXiv
- Published version: ACM Transactions on Graphics, 36 (4), 1.
This publication has 16 references indexed in Scilit:
- Data‐Driven Shape Analysis and ProcessingComputer Graphics Forum, 2016
- 3D Mesh Labeling via Deep Convolutional Neural NetworksACM Transactions on Graphics, 2015
- 3D Shape Segmentation and Labeling via Extreme Learning MachineComputer Graphics Forum, 2014
- Co‐Segmentation of 3D Shapes via Subspace ClusteringComputer Graphics Forum, 2012
- Unsupervised co-segmentation of a set of shapes via descriptor-space spectral clusteringACM Transactions on Graphics, 2011
- Symmetry Hierarchy of Man‐Made ObjectsComputer Graphics Forum, 2011
- On-Line Expectation–Maximization Algorithm for latent Data ModelsJournal of the Royal Statistical Society Series B: Statistical Methodology, 2009
- Fast approximate energy minimization via graph cutsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2001
- Using spin images for efficient object recognition in cluttered 3D scenesIEEE Transactions on Pattern Analysis and Machine Intelligence, 1999
- An algorithm for suffix strippingProgram: electronic library and information systems, 1980