UrBLEND: Building Model Synthesis From Incomplete Point Cloud With Gnervative Prios

Building reconstruction often relies on point clouds from LiDAR or visual reconstruction frontends. Noise, occlusion, and uneven sampling make these observations incomplete and uncertain. Recovering complete geometry from such sparse evidence is underconstrained, motivating pretrained shape priors. To support learning and evaluation in this setting, we introduce CityEXP, a scalable data-construction pipeline and benchmark protocol. Agent-coordinated procedural city generation preserves building identities and detailed geometry; high-fidelity scene rendering and visual reconstruction produce incomplete point observations paired with these targets. Our baseline, UrBlend, adapts Hunyuan3D-Omni's pretrained shape prior to building observations. Prepared surfaces supply latent training targets across compatible geometry sources. A pretrained surface decoder produces meshes; separately trained structural decoders produce wireframes after task adaptation. On CityEXP, the baseline achieves canonical-shape $F_{.02}$ of $54.38\%$ and Chamfer distance of $26.34\times 10^{-3}$. CityEXP and UrBlend establish a benchmark and unified baseline for prior-guided building reconstruction.