Mastering Spatial Graph Prediction of Road Networks
This work addresses the challenge of accurate road network prediction for applications in mapping and urban planning, offering a novel approach with improved performance.
The paper tackles the problem of predicting road networks from satellite images by introducing a graph-based reinforcement learning framework that simulates edge additions, which outperforms supervised methods on benchmark datasets and shows robustness under occlusions.
Accurately predicting road networks from satellite images requires a global understanding of the network topology. We propose to capture such high-level information by introducing a graph-based framework that simulates the addition of sequences of graph edges using a reinforcement learning (RL) approach. In particular, given a partially generated graph associated with a satellite image, an RL agent nominates modifications that maximize a cumulative reward. As opposed to standard supervised techniques that tend to be more restricted to commonly used surrogate losses, these rewards can be based on various complex, potentially non-continuous, metrics of interest. This yields more power and flexibility to encode problem-dependent knowledge. Empirical results on several benchmark datasets demonstrate enhanced performance and increased high-level reasoning about the graph topology when using a tree-based search. We further highlight the superiority of our approach under substantial occlusions by introducing a new synthetic benchmark dataset for this task.