In this work, we introduce CC3D, a conditional generative model that synthesizes complex 3D scenes conditioned on 2D semantic scene layouts, trained using single-view images. Different from most existing 3D GANs that limit their applicability to aligned single objects, we focus on generating complex scenes with multiple objects, by modeling the compositional nature of 3D scenes. By devising a 2D layout-based approach for 3D synthesis and implementing a new 3D field representation with a stronger geometric inductive bias, we have created a 3D GAN that is both efficient and of high quality, while allowing for a more controllable generation process. Our evaluations on synthetic 3D-FRONT and real-world KITTI-360 datasets demonstrate that our model generates scenes of improved visual and geometric quality in comparison to previous works.
@article{arxiv.2303.12074,
title = {CC3D: Layout-Conditioned Generation of Compositional 3D Scenes},
author = {Sherwin Bahmani and Jeong Joon Park and Despoina Paschalidou and Xingguang Yan and Gordon Wetzstein and Leonidas Guibas and Andrea Tagliasacchi},
journal= {arXiv preprint arXiv:2303.12074},
year = {2023}
}