Global-to-local generative model for 3D shapes
Lists
Only you see this
Abstract
We introduce a generative model for 3D man-made shapes. The presented method takes a global-to-local (G2L) approach. An adversarial network (GAN) is built first to construct the overall structure of the shape, segmented and labeled into parts. A novel conditional auto-encoder (AE) is then augmented to act as a part-level refiner. The GAN, associated with additional local discriminators and quality losses, synthesizes a voxel-based model, and assigns the voxels with part labels that are represented in separate channels. The AE is trained to amend the initial synthesis of the parts, yielding more plausible part geometries. We also introduce new means to measure and evaluate the performance of an adversarial generative model. We demonstrate that our global-to-local generative model produces significantly better results than a plain three-dimensional GAN, in terms of both their shape variety and the distribution with respect to the training data.
BibTeX
@article{wang2018global,
author = {Hao Wang and Nadav Schor and Ruizhen Hu and Haibin Huang and Daniel Cohen-Or and Hui Huang},
title = {{Global-to-local generative model for 3D shapes}},
journal = {ACM Trans. Graphics},
year = {2018},
doi = {10.1145/3272127.3275025},
}Loading related content...