3D-aware scene manipulation via inverse graphics
Name
7459-3d-aware-scene-manipulation-via-inverse-graphics.pdf
Description
Published version
Size
4.72 MB
Format
Adobe PDF
Checksum (MD5)
707eb7e273a5f1973feaf3d941f2faa3
Author(s)
Yao, Shunyu
Hsu, Tzu Ming
Zhu, Jun-Yan
Wu, Jiajun
Torralba, Antonio
Freeman, William T.
Tenenbaum, Joshua B.
Date Issued
2018
Journal
Advances in Neural Information Processing Systems
Publisher
Neural Information Processing Systems Foundation, Inc.
Citation
Yao, Shunyu, et al., "3D-aware scene manipulation via inverse graphics." Advances in Neural Information Processing Systems 31 (2018) url https://papers.nips.cc/book/advances-in-neural-information-processing-systems-31-2018
Version
Final published version
Abstract
We aim to obtain an interpretable, expressive, and disentangled scene representation that contains comprehensive structural and textural information for each object. Previous scene representations learned by neural networks are often uninterpretable, limited to a single object, or lacking 3D knowledge. In this work, we propose 3D scene de-rendering networks (3D-SDN) to address the above issues by integrating disentangled representations for semantics, geometry, and appearance into a deep generative model. Our scene encoder performs inverse graphics, translating a scene into a structured object-wise representation. Our decoder has two components: a differentiable shape renderer and a neural texture generator. The disentanglement of semantics, geometry, and appearance supports 3D-aware scene manipulation, e.g., rotating and moving objects freely while keeping the consistent shape and texture, and changing the object appearance without affecting its shape. Experiments demonstrate that our editing scheme based on 3D-SDN is superior to its 2D counterpart. ©2018 Poster presentation at the 32nd annual Conference on Neural Information Processing Systems (NIPS 2018), December 3-5, 2018, Montréal, Québec.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
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://papers.nips.cc/paper/7459-3d-aware-scene-manipulation-via-inverse-graphics
