{"ID":5675946,"CreatedAt":"2026-07-03T01:40:09.565152011Z","UpdatedAt":"2026-07-04T18:27:13.724466756Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.01370","arxiv_id":"2607.01370","title":"MapDreamer: Aerial Imagery Conditioned Latent Diffusion for Lane-Level Map Generation","abstract":"High definition map generation is essential for autonomous driving, yet remains a labor-intensive process at scale. We present MapDreamer, a generative diffusion model that synthesizes lane-level vector maps with explicit topology directly from a single aerial image. MapDreamer learns a compact latent representation of lane centerlines and their topological relations using a variational autoencoder and predicts graphs with a transformer-based latent diffusion model. To align generated maps with the observed scene, we condition each denoising step on dense aerial features injected through cross-attention. To handle the varying number of lanes across scenes, we propose a lane cardinality module paired with background ghost lane latents, a learned buffer that prevents slot collapse during diffusion. Furthermore, we introduce a sliding-window global graph aggregation strategy that stitches local tiles into city-scale maps while preserving connectivity through encoded lane boundaries. Experiments on UrbanLaneGraph derived from Argoverse 2 show improved geometric and topological fidelity over non-generative baselines.","short_abstract":"High definition map generation is essential for autonomous driving, yet remains a labor-intensive process at scale. We present MapDreamer, a generative diffusion model that synthesizes lane-level vector maps with explicit topology directly from a single aerial image. MapDreamer learns a compact latent representation of...","url_abs":"https://arxiv.org/abs/2607.01370","url_pdf":"https://arxiv.org/pdf/2607.01370v1","authors":"[\"Julian Brandes\",\"Philipp Crocoll\",\"Wolfram Burgard\"]","published":"2026-07-01T18:33:38Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Diffusion Model\",\"Transformer\"]","has_code":false}