InfiniCity: Infinite-Scale City Synthesis

Abstract

Toward infinite-scale 3D city synthesis, we propose a novel framework, InfiniCity, which constructs and renders an unconstrainedly large and 3D-grounded environment from random noises. InfiniCity decomposes the seemingly impractical task into three feasible modules, taking advantage of both 2D and 3D data. First, an infinite-pixel image synthesis module generates arbitrary-scale 2D maps from the bird's-eye view. Next, an octree-based voxel completion module lifts the generated 2D map to 3D octrees. Finally, a voxel-based neural rendering module texturizes the voxels and renders 2D images. InfiniCity can thus synthesize arbitrary-scale and traversable 3D city environments. We quantitatively and qualitatively demonstrate the efficacy of the proposed framework.

Cite

Text

Lin et al. "InfiniCity: Infinite-Scale City Synthesis." International Conference on Computer Vision, 2023. doi:10.1109/ICCV51070.2023.02085

Markdown

[Lin et al. "InfiniCity: Infinite-Scale City Synthesis." International Conference on Computer Vision, 2023.](https://mlanthology.org/iccv/2023/lin2023iccv-infinicity/) doi:10.1109/ICCV51070.2023.02085

BibTeX

@inproceedings{lin2023iccv-infinicity,
  title     = {{InfiniCity: Infinite-Scale City Synthesis}},
  author    = {Lin, Chieh Hubert and Lee, Hsin-Ying and Menapace, Willi and Chai, Menglei and Siarohin, Aliaksandr and Yang, Ming-Hsuan and Tulyakov, Sergey},
  booktitle = {International Conference on Computer Vision},
  year      = {2023},
  pages     = {22808-22818},
  doi       = {10.1109/ICCV51070.2023.02085},
  url       = {https://mlanthology.org/iccv/2023/lin2023iccv-infinicity/}
}