DOGE: Differentiable Bezier Graph Optimization for Road Network Extraction
This addresses the challenge of accurately modeling curvilinear road geometry for automated mapping, representing a novel paradigm rather than an incremental improvement.
The paper tackles the problem of extracting road networks from aerial imagery by introducing a differentiable Bézier Graph representation that eliminates the need for vector ground-truth, achieving state-of-the-art results on SpaceNet and CityScale benchmarks.
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.