AI Paper Atlas

Research map / Point clouds / Segmentation and detection

BuildingWorld: A Structured 3D Building Dataset for Urban Foundation Models

Shangfeng Huang, Ruisheng Wang, Xin Wang

AAAI 2026 · Point clouds › Segmentation and detection · approach: Scene completion and instance segmentation · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
train on simulated point clouds instead of real point cloudsPBWR · Building3D real testACO: 0.22 -> 0.36Hurt
train on simulated point clouds instead of real point cloudsPBWR · Building3D real testEdge F1: 0.76 -> 0.65Hurt
train on simulated point clouds instead of real point cloudsEdgeDiff · Building3D real testCorner F1: 0.84 -> 0.76Hurt
train on simulated point clouds instead of real point cloudsBWFormer · Building3D real testCorner F1: 0.88 -> 0.82Hurt
train on simulated point clouds instead of real point cloudsBWFormer · Building3D real testACO: 0.20 -> 0.22No clear effect
train on simulated data vs real data across three methodsPBWR/EdgeDiff/BWFormer · Building3D real testreconstruction metrics: e.g. Edge F1 0.79 -> 0.68 (EdgeDiff)Mixed

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy