生成式高斯泼溅用于无界3D城市生成
Generative Gaussian Splatting for Unbounded 3D City Generation
AI总结：
提出GaussianCity，一个生成式高斯泼溅框架，通过BEV-Point紧凑表示和空间感知解码器，实现单次前向传播高效生成无界3D城市，速度较CityDreamer提升60倍。
摘要：
基于NeRF的方法在3D城市生成中展现出有前景的生成结果，但计算效率低下。近年来，3D高斯泼溅（3D-GS）已成为对象级3D生成的高效替代方案。然而，将3D-GS从有限尺度的3D物体和人体扩展到无限尺度的3D城市并非易事。无界3D城市生成需要将点扩展到数十亿，这带来了巨大的存储开销（内存不足问题），对于覆盖10km²的城市场景，通常需要数百GB的显存。在本文中，我们提出了GaussianCity，一个生成式高斯泼溅框架，致力于通过单次前向传播高效合成无界3D城市。我们的关键见解有两点：1）紧凑的3D场景表示：我们引入BEV-Point作为高度紧凑的中间表示，确保无界场景的显存占用增长保持恒定，从而实现无界城市生成。2）空间感知的高斯属性解码器：我们提出了空间感知的BEV-Point解码器来生成3D高斯属性，该解码器利用点序列化器整合BEV点的结构和上下文特征。大量实验表明，GaussianCity在无人机视角和街景视角的3D城市生成中均达到了最先进的性能。值得注意的是，与CityDreamer相比，GaussianCity表现出更优越的性能，速度提升60倍（10.72 FPS对比0.18 FPS）。
英文摘要：
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).
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
