Top2Pano: 学习从俯视视角生成室内全景图
Top2Pano: Learning to Generate Indoor Panoramas from Top-Down View
AI总结：
针对俯视生成室内全景图的结构与真实感难题，提出端到端模型Top2Pano，结合体素渲染与ControlNet扩散优化，在多数据集上优于基线且泛化性好。
摘要：
从二维俯视视角生成沉浸式360°室内全景图在虚拟现实、室内设计、房地产与机器人领域均有应用。该任务因缺乏明确三维结构，且需满足几何一致性与照片级真实感而颇具挑战。我们提出Top2Pano，一种用于从俯视视角合成真实室内全景图的端到端模型。该方法先估计体素占据率以推断三维结构，再通过体素渲染生成粗略的彩色与深度全景图，以此引导基于扩散模型、采用ControlNet（控制网络）的优化阶段，提升真实感与结构保真度。在两个数据集上的评估表明，Top2Pano性能优于基线模型，能有效重建几何结构、遮挡关系与空间布局，且泛化性良好，可从示意图式楼层平面图生成高质量全景图。研究结果凸显了Top2Pano在衔接俯视视图与沉浸式室内合成方面的潜力。
英文摘要：
Generating immersive 360° indoor panoramas from 2D top-down views has applications in virtual reality, interior design, real estate, and robotics. This task is challenging due to the lack of explicit 3D structure and the need for geometric consistency and photorealism. We propose Top2Pano, an end-to-end model for synthesizing realistic indoor panoramas from top-down views. Our method estimates volumetric occupancy to infer 3D structures, then uses volumetric rendering to generate coarse color and depth panoramas. These guide a diffusion-based refinement stage using ControlNet, enhancing realism and structural fidelity. Evaluations on two datasets show Top2Pano outperforms baselines, effectively reconstructing geometry, occlusions, and spatial arrangements. It also generalizes well, producing high-quality panoramas from schematic floorplans. Our results highlight Top2Pano's potential in bridging top-down views with immersive indoor synthesis.
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。
