ACPV-Net: All-Class Polygonal Vectorization for Seamless Vector Map Generation from Aerial Imagery

2026-03-17

AI Summary

This work addresses the challenge of topological inconsistencies—such as boundary duplication, gaps, or overlaps—in multi-class land cover vectorization from aerial imagery. To this end, the authors propose ACPV-Net, a unified framework that introduces the first all-category polygon vectorization (ACPV) task. The method integrates a semantic supervision mechanism to jointly optimize semantic awareness and geometric primitive generation, and incorporates a shared-boundary topological reconstruction module to enforce global consistency. The study establishes Deventer-512, the first public benchmark for this task, on which ACPV-Net significantly outperforms existing single-category approaches. Furthermore, it achieves state-of-the-art performance on the WHU-Building dataset for single-category vectorization, demonstrating superior balance among semantic accuracy, geometric precision, and topological consistency.

Technology Category

• Computer Vision: Remote Sensing / Geospatial AI
• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

We tackle the problem of generating a complete vector map representation from aerial imagery in a single run: producing polygons for all land-cover classes with shared boundaries and without gaps or overlaps. Existing polygonization methods are typically class-specific; extending them to multiple classes via per-class runs commonly leads to topological inconsistencies, such as duplicated edges, gaps, and overlaps. We formalize this new task as All-Class Polygonal Vectorization (ACPV) and release the first public benchmark, Deventer-512, with standardized metrics jointly evaluating semantic fidelity, geometric accuracy, vertex efficiency, per-class topological fidelity and global topological consistency. To realize ACPV, we propose ACPV-Net, a unified framework introducing a novel Semantically Supervised Conditioning (SSC) mechanism coupling semantic perception with geometric primitive generation, along with a topological reconstruction that enforces shared-edge consistency by design. While enforcing such strict topological constraints, ACPV-Net surpasses all class-specific baselines in polygon quality across classes on Deventer-512. It also applies to single-class polygonal vectorization without any architectural modification, achieving the best-reported results on WHU-Building. Data, code, and models will be released at: https://github.com/HeinzJiao/ACPV-Net.

Problem

• vector map generation
• polygonal vectorization
• aerial imagery
• topological consistency
• land-cover classes

Innovation

• All-Class Polygonal Vectorization
• Semantically Supervised Conditioning
• Topological Consistency
• Vector Map Generation
• Aerial Imagery