Unsupervised Primitive Discovery for Improved 3D Generative Modeling

Salman Khan, Yulan Guo, Munawar HAYAT, Nick Barnes

Research output: A Conference proceeding or a Chapter in BookConference contributionpeer-review


3D shape generation is a challenging problem due to the high-dimensional output space and complex part configurations
of real-world objects. As a result, existing algorithms experience difficulties in accurate generative modeling of 3D shapes. Here, we propose a novel factorized generative model for 3D shape generation that sequentially transitions from coarse to fine scale shape generation. To this end, we introduce an unsupervised primitive discovery algorithm based
on a higher-order conditional random field model. Using the primitive parts for shapes as attributes, a parameterized
3D representation is modeled in the first stage. This representation is further refined in the next stage by adding fine
scale details to shape. Our results demonstrate improved representation ability of the generative model and better
quality samples of newly generated 3D shapes. Further, our primitive generation approach can accurately parse common
objects into a simplified representation.
Original languageEnglish
Title of host publicationIEEE Conference on Computer Vision and Pattern Recognition
Number of pages10
Publication statusIn preparation - 2019
EventIEEE Conference on Computer Vision and Pattern Recognition - Long Beach, United States
Duration: 15 Jun 201920 Jun 2019


ConferenceIEEE Conference on Computer Vision and Pattern Recognition
Abbreviated titleCVPR 2019
Country/TerritoryUnited States
CityLong Beach
Internet address


Dive into the research topics of 'Unsupervised Primitive Discovery for Improved 3D Generative Modeling'. Together they form a unique fingerprint.

Cite this