InfiniCity: Infinite-Scale City Synthesis

TL;DR

InfiniCity introduces a novel framework for generating and rendering infinitely large, detailed 3D city environments by combining 2D map synthesis, 3D voxel completion, and neural rendering, enabling scalable and interactive city modeling.

Contribution

The paper presents a new modular framework that synthesizes and renders infinite-scale 3D cities from random noise, integrating 2D and 3D data for scalable environment creation.

Findings

Successfully generates arbitrary-scale 3D city environments.

Demonstrates high-quality synthesis and rendering results.

Enables flexible editing of large city models.

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, 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/