用可编辑的3D组件生成城市场景，更省内存、更快、更好调。
PrITTI: Primitive-based Generation of Controllable and Editable 3D Semantic Urban Scenes
- 用向量化的物体和栅格化地面构建混合表示，支持结构化操作
- 在KITTI-360上实现最优生成质量，内存更低、推理更快
- 适合需要可控编辑的城市场景生成任务
现有3D语义城市场景生成方法多依赖体素表示，存在分辨率固定、难编辑、内存占用高等问题。本文提出基于几何原型的范式，用紧凑且语义明确的3D元素构建场景，更易操作与组合。为此，我们引入PrITTI——一种利用向量化物体原型和栅格化地面的潜在扩散模型，生成多样化、可控制、可编辑的3D语义城市场景。该混合表示构建出结构化的潜在空间，支持物体级与地面级操作。在KITTI-360上的实验表明，基于原型的表示充分发挥了扩散变换器的能力，相比体素方法，在生成质量上达到当前最优，同时内存更低、推理更快、编辑性更强。除生成外，PrITTI还支持场景编辑、补全、扩展及逼真街景合成等下游应用。代码与更多结果见https://raniatze.github.io/pritti/。
原文摘要 · Abstract (English)
Existing approaches to 3D semantic urban scene generation predominantly rely on voxel-based representations, which are bound by fixed resolution, challenging to edit, and memory-intensive in their dense form. In contrast, we advocate for a primitive-based paradigm where urban scenes are represented using compact, semantically meaningful 3D elements that are easy to manipulate and compose. To this end, we introduce PrITTI, a latent diffusion model that leverages vectorized object primitives and rasterized ground surfaces for generating diverse, controllable, and editable 3D semantic urban scenes. This hybrid representation yields a structured latent space that facilitates object- and ground-level manipulation. Experiments on KITTI-360 show that primitive-based representations unlock the full capabilities of diffusion transformers, achieving state-of-the-art 3D scene generation quality with lower memory requirements, faster inference, and greater editability than voxel-based methods. Beyond generation, PrITTI supports a range of downstream applications, including scene editing, inpainting, outpainting, and photo-realistic street-view synthesis. The source code and more results can be found at https://raniatze.github.io/pritti/.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。