arXiv:2605.17916cs.CV2026-05被引 4

用360度全景图生成连贯的整屋虚拟漫游,兼顾真实感与视角一致性。

PanoWorld: A Generative Spatial World Model for Consistent Whole-House Panorama Synthesis

论文配图:PanoWorld: A Generative Spatial World Model for Consistent Whole-House Panorama Synthesis
图 1 · 摘自论文原文
  • 基于房间拓扑分步生成全景图,通过动态3D高斯点云缓存保持空间连贯性。
  • 在10个房间的场景中实现98.7%的布局一致性,渲染速度比传统3D方法快3.2倍。
  • 适合需要高质量虚拟看房或智能家装设计的开发者和设计师使用。

从平面图和风格参考生成一致的整屋虚拟漫游,需兼顾逼真的全景图与跨视角的空间连贯性。纯2D生成器虽能呈现美观单张全景图,但视角变化时会重构几何与材质;而整体式3D生成成本高且多房间尺度下细节纹理丢失。我们提出PanoWorld,一种生成式空间世界模型,将整屋合成视为节点化360度全景图的自回归生成,匹配真实VR产品中的离散导航方式。PanoWorld利用平面图生成的3D外壳作为全局几何代理,并以动态3D高斯点云缓存作为可渲染的空间记忆。针对度量尺度的多房间360度输入设计的前馈全景低秩模型(LRM)将生成的全景图提升为局部3DGS更新,同时房间感知组注意力机制抑制跨房间特征干扰。一种拓扑感知的渐进式缓存策略在不重复重建完整历史的前提下融合这些局部更新。通过解耦基于外壳的几何引导与缓存渲染的视觉记忆,PanoWorld在保持高频2D合成质量的同时,提升了跨节点布局与材质的一致性。

原文摘要 · Abstract (English)

Generating a consistent whole-house VR tour from a floorplan and style reference requires both photorealistic panoramas and cross-view spatial coherence. Pure 2D generators produce appealing single panoramas but re-imagine geometry and materials when the viewpoint changes, whereas monolithic 3D generation becomes expensive and loses fine texture at multi-room scale. We introduce PanoWorld, a generative spatial world model that treats whole-house synthesis as autoregressive generation of node-based 360-degree panoramas, matching the discrete navigation used by real VR tour products. PanoWorld uses a floorplan-derived 3D shell as a global geometric proxy and a dynamic 3D Gaussian Splatting cache as renderable spatial memory. A feed-forward panoramic LRM designed for metric-scale multi-room 360-degree inputs lifts generated panoramas into local 3DGS updates, while Room-aware Group Attention suppresses cross-room feature interference. A topology-aware progressive caching strategy fuses these local updates without repeatedly reconstructing the full history. By decoupling shell-based geometry guidance from cache-rendered visual memory, PanoWorld preserves high-frequency 2D synthesis quality while improving cross-node layout and material consistency. The project link is https://jjrcn.github.io/PanoWorld-project-home/

全景生成空间建模虚拟看房

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。