mlsanityData to 14 Oct 2026

Click2Poly: A VLM for vector mapping buildings and walls

arXiv 2608.11424 ↗First posted 11 Aug 2026cs.LG cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Accurate vector mapping of buildings and walls is critical for geospatial applications but remains a labor-intensive process. While recent deep learning methods have improved automatic extraction, in order to meet cartographic standards they always require a human to perform quality control and fix complex cases in the extraction. We present Click2Poly, a human-in-the-loop AI assistant designed to speed up this manual step. Extending the Florence-2 Vision Language Model (VLM), Click2Poly responds to user clicks by editing the building or wall vector layer directly. Implemented as a QGIS plugin, Click2Poly speeds up the manual editing of building and wall vector layers in a real-world production environment.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 9 of its 16 references that are in the map. First posted on arXiv 11 Aug 2026.

Builds on

9 of 16 references.

References · 9

  1. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  2. 2023Segment Anythingcited by 8,234
  3. 2025SAM 3: Segment Anything with Conceptscited by 906
  4. 2023Florence-2: Advancing a Unified Representation for a Variety of Vision Taskscited by 410
  5. 2018Efficient Interactive Annotation of Segmentation Datasets with Polygon-RNN++cited by 120
  6. 2017Annotating Object Instances with a Polygon-RNNcited by 88
  7. 2024Pix2Poly: A Sequence Prediction Method for End-to-end Polygonal Building Footprint Extraction from Remote Sensing Imagerycited by 8
  8. 2024RoIPoly: Vectorized Building Outline Extraction Using Vertex and Logit Embeddingscited by 6
  9. 2024PolyFootNet: Extracting Polygonal Building Footprints in Off-Nadir Remote Sensing Imagescited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025VectorLLM: Human-like Extraction of Structured Building Contours vis Multimodal LLMs
  2. 2024Vision Language Models Can Parse Floor Plan Maps
  3. 2026Vector Map as Language: Toward Unified Remote Sensing Vector Mapping
  4. 2026CoMa: Contextual Massing Generation with Vision-Language Models
  5. 2026USAI-Quant: A Quantitative Reasoning Benchmark for Vision-Language Models in Built Environments
  6. 2025Generative AI in Map-Making: A Technical Exploration and Its Implications for Cartographers
  7. 2025PlanGPT-VL: Enhancing Urban Planning with Domain-Specific Vision-Language Models
  8. 2025Streetscape Analysis with Generative AI (SAGAI): Vision-Language Assessment and Mapping of Urban Scenes