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

TL;DR

ACPV-Net introduces a unified approach for all-class polygonal vectorization from aerial imagery, ensuring topological consistency and surpassing class-specific methods in quality, with a new benchmark dataset for evaluation.

Contribution

The paper formalizes the All-Class Polygonal Vectorization task, proposes ACPV-Net with a novel SSC mechanism and topological constraints, and releases the first benchmark dataset for comprehensive evaluation.

Findings

ACPV-Net outperforms class-specific baselines in polygon quality.

The method achieves state-of-the-art results on WHU-Building.

The benchmark Deventer-512 enables standardized evaluation of vectorization methods.

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.