Projective analysis for 3D shape segmentation

Yunhai Wang*, Minglun Gong, Tianhua Wang, Daniel Cohen-Or, Hao Zhang, Baoquan Chen

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review


We introduce projective analysis for semantic segmentation and labeling of 3D shapes. The analysis treats an input 3D shape as a collection of 2D projections, labels each projection by transferring knowledge from existing labeled images, and back-projects and fuses the labelings on the 3D shape. The image-space analysis involves matching projected binary images of 3D objects based on a novel bi-class Hausdorff distance. The distance is topology-aware by accounting for internal holes in the 2D figures and it is applied to piecewise-linearly warped object projections to compensate for part scaling and view discrepancies. Projective analysis simplifies the processing task by working in a lower-dimensional space, circumvents the requirement of having complete and well-modeled 3D shapes, and addresses the data challenge for 3D shape analysis by leveraging the massive available image data. A large and dense labeled set ensures that the labeling of a given projected image can be inferred from closely matched labeled images. We demonstrate semantic labeling of imperfect (e.g., incomplete or self-intersecting) 3D models which would be otherwise difficult to analyze without taking the projective analysis approach.

Original languageEnglish
Article number192
JournalACM Transactions on Graphics
Issue number6
StatePublished - Nov 2013


  • Bilateral symmetric Hausdorff distance
  • Projective shape analysis
  • Semantic segmentation and labeling
  • Shape matching


Dive into the research topics of 'Projective analysis for 3D shape segmentation'. Together they form a unique fingerprint.

Cite this