SOURCE-LINKED INTELLIGENCE

Multimodal Floorplan Encoding: Learning Dense Modality-Invariant Representations

arXiv · AI, language, vision and robotics · article · Sep 11, 2026 · UTC

Floorplans arise in many forms, from vector CAD drawings to raster renderings and sensor-derived density maps. This heterogeneity makes it difficult to build learning systems that transfer across modalities and support geometry-centric tasks such as alignment and retrieval. We introduce the Multimodal Floorplan Encoder (MMFE), which maps diverse 2D indoor representations into a shared dense latent grid. MMFE combines a frozen DINOv3 backbone with a trainable Dense Prediction Transformer (DPT) head, and is trained with a per-cell Information Noise-Contrastive Estimation (InfoNCE) objective that

Read original source ↗ Open in workspace

recordType

paper

region

Global