Skip to main content

Interactive 3D Modeling with a Generative Adversarial Network

Author(s): Liu, Jerry; Yu, Fisher; Funkhouser, Thomas

To refer to this page use:
Abstract: We propose the idea of using a generative adversarial network (GAN) to assist users in designing real-world shapes with a simple interface. Users edit a voxel grid with a Minecraft-like interface. Yet they can execute a SNAP command at any time, which transforms their rough model into a desired shape that is both similar and realistic. They can edit and snap until they are satisfied with the result. The advantage of this approach is to assist novice users to create 3D models characteristic of the training data by only specifying rough edits. Our key contribution is to create a suitable projection operator around a 3D-GAN that maps an arbitrary 3D voxel input to a latent vector in the shape manifold of the generator that is both similar in shape to the input but also realistic. Experiments show our method is promising for computer-assisted interactive modeling.
Publication Date: 2017
Citation: Liu, Jerry, Fisher Yu, and Thomas Funkhouser. "Interactive 3D modeling with a generative adversarial network." In International Conference on 3D Vision (3DV) (2017): pp. 126-134. doi:10.1109/3DV.2017.00024
DOI: 10.1109/3DV.2017.00024
EISSN: 2475-7888
Pages: 126 - 134
Type of Material: Conference Article
Journal/Proceeding Title: International Conference on 3D Vision
Version: Author's manuscript

Items in OAR@Princeton are protected by copyright, with all rights reserved, unless otherwise indicated.