Skip to content

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#diffusion models Dataset Open access Sep 2026

Data supporting the publication: LDPoly: Latent Diffusion for Polygonal Road Outline Extraction in Large-Scale Topographic Mapping

The LDPoly Dutch Polygonal Road Outline Extraction Benchmark is a processed dataset for extracting vectorized road-surface polygons from high-resolution aerial imagery. It was used in the paper LDPoly: Latent Diffusion for Polygonal Road Outline Extraction in Large-Scale Topographic Mapping.The dataset contains RGB aerial imagery and corresponding road polygon annotations from Deventer, Enschede, and Giethoorn in the Netherlands. Deventer is used for training and in-region testing, while Enschede and Giethoorn serve as unseen cross-region test areas covering urban, suburban, rural, and forested environments.The original 4,000 × 4,000 images at 7.5 cm spatial resolution were downsampled and divided into non-overlapping 256 × 256 patches for model development and evaluation. The dataset supports polygonal road outline extraction, road segmentation, and cross-region generalization studies. Detailed file organization, annotation specifications, and preprocessing information are provided in the accompanying README.The dataset is derived from the Map2ImLas dataset through further processing and reorganization of the source data.

W. Jiao MSc, Hao Cheng, George Vosselman et al. · 0 citations
#diffusion models Open access Sep 2026

Source code for "LDPoly: Latent diffusion for polygonal road outline extraction in large-scale topographic mapping"

This software contains the official implementation of LDPoly, a novel diffusion-model-based framework specifically designed for polygonal road outline extraction from high-resolution aerial imagery. It employs a dual-latent diffusion model that jointly diffuses and denoises road masks and keypoint heatmaps, which are subsequently vectorized into polygonal road outlines. The repository includes model implementation, training and inference configurations, polygonization procedures, evaluation scripts, and instructions for use. This archived version corresponds to the code associated with the ISPRS 2025 paper “LDPoly: Latent diffusion for polygonal road outline extraction in large-scale topographic mapping.”

W. Jiao MSc, Hao Cheng, George Vosselman et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.