PrITTI：基于基元的可控可编辑三维语义城市场景生成
PrITTI: Primitive-based Generation of Controllable and Editable 3D Semantic Urban Scenes
用向量化物体基元加栅格化地面构成混合表示，替代体素作为三维语义场景的生成载体，使潜扩散模型能在结构化潜空间里做物体级与地面级编辑；做三维场景生成或编辑时可借鉴这种「基元+地面」的紧凑表示与对应的 inpainting/outpainting 流程。
原文依据 a latent diffusion model that leverages vectorized object primitives and rasterized ground surfaces
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论现有的三维语义城市场景生成方法主要依赖基于体素的表示，这类表示受限于固定分辨率、难以编辑，且其稠密形式内存开销大。相比之下，我们主张采用基于基元的范式，即用紧凑、具有语义意义且易于操作与组合的三维元素来表示城市场景。为此，我们提出 PrITTI，一种潜扩散模型，利用向量化的物体基元与栅格化的地面表面来生成多样、可控且可编辑的三维语义城市场景。这种混合表示产生了结构化的潜空间，便于进行物体级与地面级的操作。在 KITTI-360 上的实验表明，基于基元的表示充分释放了扩散 Transformer 的能力，在三维场景生成质量上达到最优，同时相比基于体素的方法具有更低的内存需求、更快的推理速度和更强的可编辑性。除生成之外，PrITTI 还支持一系列下游应用，包括场景编辑、图像补全、图像外扩以及照片级真实的街景合成。
英文原文摘要 1160 字符
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.