DOGE: Differentiable Bezier Graph Optimization for Road Network Extraction

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Sun, Jiahui, Lu, Junran, Yin, Jinhui, Xu, Yishuo, Li, Yuanqi, Guo, Yanwen
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908673566048256
author Sun, Jiahui
Lu, Junran
Yin, Jinhui
Xu, Yishuo
Li, Yuanqi
Guo, Yanwen
author_facet Sun, Jiahui
Lu, Junran
Yin, Jinhui
Xu, Yishuo
Li, Yuanqi
Guo, Yanwen
contents Automatic extraction of road networks from aerial imagery is a fundamental task, yet prevailing methods rely on polylines that struggle to model curvilinear geometry. We maintain that road geometry is inherently curve-based and introduce the Bézier Graph, a differentiable parametric curve-based representation. The primary obstacle to this representation is to obtain the difficult-to-construct vector ground-truth (GT). We sidestep this bottleneck by reframing the task as a global optimization problem over the Bézier Graph. Our framework, DOGE, operationalizes this paradigm by learning a parametric Bézier Graph directly from segmentation masks, eliminating the need for curve GT. DOGE holistically optimizes the graph by alternating between two complementary modules: DiffAlign continuously optimizes geometry via differentiable rendering, while TopoAdapt uses discrete operators to refine its topology. Our method sets a new state-of-the-art on the large-scale SpaceNet and CityScale benchmarks, presenting a new paradigm for generating high-fidelity vector maps of road networks. We will release our code and related data.
format Preprint
id arxiv_https___arxiv_org_abs_2511_19850
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DOGE: Differentiable Bezier Graph Optimization for Road Network Extraction
Sun, Jiahui
Lu, Junran
Yin, Jinhui
Xu, Yishuo
Li, Yuanqi
Guo, Yanwen
Computer Vision and Pattern Recognition
Graphics
Automatic extraction of road networks from aerial imagery is a fundamental task, yet prevailing methods rely on polylines that struggle to model curvilinear geometry. We maintain that road geometry is inherently curve-based and introduce the Bézier Graph, a differentiable parametric curve-based representation. The primary obstacle to this representation is to obtain the difficult-to-construct vector ground-truth (GT). We sidestep this bottleneck by reframing the task as a global optimization problem over the Bézier Graph. Our framework, DOGE, operationalizes this paradigm by learning a parametric Bézier Graph directly from segmentation masks, eliminating the need for curve GT. DOGE holistically optimizes the graph by alternating between two complementary modules: DiffAlign continuously optimizes geometry via differentiable rendering, while TopoAdapt uses discrete operators to refine its topology. Our method sets a new state-of-the-art on the large-scale SpaceNet and CityScale benchmarks, presenting a new paradigm for generating high-fidelity vector maps of road networks. We will release our code and related data.
title DOGE: Differentiable Bezier Graph Optimization for Road Network Extraction
topic Computer Vision and Pattern Recognition
Graphics
url https://arxiv.org/abs/2511.19850