Bookmark Saya

arXiv Open Access 2023

InfiniCity: Infinite-Scale City Synthesis

Chieh Hubert Lin Hsin-Ying Lee Willi Menapace Menglei Chai Aliaksandr Siarohin +2 lainnya
Lihat Sumber

Abstrak

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, and allow flexible and interactive editing from users. We quantitatively and qualitatively demonstrate the efficacy of the proposed framework. Project page: https://hubert0527.github.io/infinicity/

Topik & Kata Kunci

cs.CV cs.AI cs.GR cs.LG

Penulis (7)

C

Chieh Hubert Lin

H

Hsin-Ying Lee

W

Willi Menapace

M

Menglei Chai

A

Aliaksandr Siarohin

M

Ming-Hsuan Yang

S

Sergey Tulyakov

Format Sitasi

APA MLA BibTeX
Lin, C.H., Lee, H., Menapace, W., Chai, M., Siarohin, A., Yang, M. et al. (2023). InfiniCity: Infinite-Scale City Synthesis. https://arxiv.org/abs/2301.09637

Akses Cepat

Lihat di Sumber
Informasi Jurnal
Tahun Terbit
2023
Bahasa
en
Sumber Database
arXiv
Akses
Open Access ✓