3D city generation with NeRF-based methods shows promising generation results but is computationally inefficient. Recently 3D Gaussian Splatting (3D-GS) has emerged as a highly efficient alternative for object-level 3D generation. However, adapting 3D-GS from finite-scale 3D objects and humans to infinite-scale 3D cities is non-trivial. Unbounded 3D city generation entails significant storage overhead (out-of-memory issues), arising from the need to expand points to billions, often demanding hundreds of Gigabytes of VRAM for a city scene spanning 10km^2. In this paper, we propose GaussianCity, a generative Gaussian Splatting framework dedicated to efficiently synthesizing unbounded 3D cities with a single feed-forward pass. Our key insights are two-fold: 1) Compact 3D Scene Representation: We introduce BEV-Point as a highly compact intermediate representation, ensuring that the growth in VRAM usage for unbounded scenes remains constant, thus enabling unbounded city generation. 2) Spatial-aware Gaussian Attribute Decoder: We present spatial-aware BEV-Point decoder to produce 3D Gaussian attributes, which leverages Point Serializer to integrate the structural and contextual characteristics of BEV points. Extensive experiments demonstrate that GaussianCity achieves state-of-the-art results in both drone-view and street-view 3D city generation. Notably, compared to CityDreamer, GaussianCity exhibits superior performance with a speedup of 60 times (10.72 FPS v.s. 0.18 FPS).
使用基于NeRF的方法进行3D城市生成虽然展示了有前景的生成结果，但计算效率低下。最近，3D高斯涂抹（3D-GS）作为一种高效的对象级3D生成方法浮现出来。然而，将3D-GS从有限规模的3D对象和人类适应到无限规模的3D城市并非易事。无界3D城市生成涉及显著的存储开销（内存溢出问题），因为需要将点扩展到数十亿，通常需要数百吉字节的VRAM以支持覆盖10平方公里的城市场景。在本文中，我们提出了GaussianCity，一个专用于高效合成无界3D城市的生成高斯涂抹框架，它仅通过一次前馈传递即可完成。我们的关键洞察有两点：1) 紧凑的3D场景表示：我们引入了BEV-Point作为一种高度紧凑的中间表示，确保无界场景中VRAM使用的增长保持恒定，从而实现无界城市生成。2) 空间感知的高斯属性解码器：我们展示了空间感知的BEV-Point解码器，以生成3D高斯属性，该解码器利用点序列化器整合了BEV点的结构和上下文特征。广泛的实验表明，GaussianCity在无人机视角和街景视角的3D城市生成中实现了业界领先的结果。值得注意的是，与CityDreamer相比，GaussianCity表现出更优的性能，速度提升了60倍（10.72 FPS vs. 0.18 FPS）。