Synthesizing 3D Shapes via Modeling Multi-view Depth Maps and Silhouettes with Deep Generative Networks
Name
mv3d_cvpr.pdf
Description
Published version
Size
2.86 MB
Format
Adobe PDF
Checksum (MD5)
559fb3a517e9f94fb0189867a27c255a
Author(s)
Soltani, Amir Arsalan
Tenenbaum, Joshua B
Date Issued
July 2017
Journal
2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Citation
Soltani, Amir Arsalan et al. “Synthesizing 3D Shapes via Modeling Multi-view Depth Maps and Silhouettes with Deep Generative Networks.” Paper presented at the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, 21-26 July 2017, IEEE © 2017 The Author(s)
Version
Author's final manuscript
Abstract
We study the problem of learning generative models of 3D shapes. Voxels or 3D parts have been widely used as the underlying representations to build complex 3D shapes; however, voxel-based representations suffer from high memory requirements, and parts-based models require a large collection of cached or richly parametrized parts. We take an alternative approach: learning a generative model over multi-view depth maps or their corresponding silhouettes, and using a deterministic rendering function to produce 3D shapes from these images. A multi-view representation of shapes enables generation of 3D models with fine details, as 2D depth maps and silhouettes can be modeled at a much higher resolution than 3D voxels. Moreover, our approach naturally brings the ability to recover the underlying 3D representation from depth maps of one or a few viewpoints. Experiments show that our framework can generate 3D shapes with variations and details. We also demonstrate that our model has out-of-sample generalization power for real-world tasks with occluded objects.
MIT Department
Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences
Terms of Use
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1109/CVPR.2017.269
