2017/05/04 by Li Yi, Leonidas Guibas, Aaron Hertzmann +3 · 41 citations
Computer Science · Engineering · #3D Shape Modeling and Analysis #Domain (mathematical analysis) #Image segmentation #Interactive and Immersive Displays #Joint (building) #Key (lock) #Labeled data #Manufacturing Process and Optimization #Pattern recognition (psychology) #Range (aeronautics) #Segmentation #cs.GR
paper · pdf · doi:10.1145/3072959.3073652
published in ACM Transactions on Graphics 36(4), 1-12 (Association for Computing Machinery)
arxiv created 2017/05/04 · arxiv updated 2017/05/05 · openalex created_date 2017/05/12 · openalex publication_date 2017/07/20 · openalex updated_date 2026/08/06
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.