Learning hierarchical shape segmentation and labeling from online repositories
Authors:
Open Access
- 20 July 2017
- journal article
- research article
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 36 (4) , 1-12
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
Funding Information
- National Science Foundation (DMS-1521608, DMS-1546206)
- Office of Naval Research (MURI N00014-13-1-0341)
- Adobe
This publication has 28 references indexed in Scilit:
- Active co-analysis of a set of shapesACM Transactions on Graphics, 2012
- Co‐Segmentation of 3D Shapes via Subspace ClusteringComputer Graphics Forum, 2012
- Symmetry Hierarchy of Man‐Made ObjectsComputer Graphics Forum, 2011
- Learning 3D mesh segmentation and labelingACM Transactions on Graphics, 2010
- A benchmark for 3D mesh segmentationACM Transactions on Graphics, 2009
- On-Line Expectation–Maximization Algorithm for latent Data ModelsJournal of the Royal Statistical Society Series B: Statistical Methodology, 2009
- On Visual Similarity Based 3D Model RetrievalComputer Graphics Forum, 2003
- Shape matching and object recognition using shape contextsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2002
- 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