Unsupervised Primitive Discovery for Improved 3D Generative Modeling
Authors:
- 1 June 2019
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 9731-9740
Abstract
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.Keywords
All Related Versions
This publication has 25 references indexed in Scilit:
- Learning Shape Abstractions by Assembling Volumetric Primitives2017
- Separating objects and clutter in indoor scenes2015
- Meta-representation of shape familiesACM Transactions on Graphics, 2014
- Recurring part arrangements in shape collectionsComputer Graphics Forum, 2014
- Box in the Box: Joint 3D Layout and Object Reasoning from Single Images2013
- Unsupervised Joint Object Discovery and Segmentation in Internet Images2013
- Unsupervised co-segmentation through region matching2012
- On Visual Similarity Based 3D Model RetrievalComputer Graphics Forum, 2003
- Human image understanding: Recent research and a theoryComputer Vision, Graphics, and Image Processing, 1985
- An Automatic Method of Solving Discrete Programming ProblemsEconometrica, 1960