Search papers, labs, and topics across Lattice.
The paper introduces CityGen, a diffusion-based generative framework for zero-label city adaptation in autonomous driving, conditioned on HD maps and city-level visual prompts. CityGen addresses the challenge of cross-city generalization by synthesizing city-style images without requiring labeled target data or city-specific annotations. Experiments on the new CityTransfer-Bench benchmark show that CityGen improves cross-city robustness across perception, segmentation, and planning tasks.
Synthesizing new city driving environments from HD maps and visual cues allows autonomous vehicles to train for new locations without needing any labeled data.
Autonomous driving systems are commonly trained and evaluated within limited geographic regions, which hinders their scalability when deployed in new cities. However, significant domain shifts in appearance, road topology, and traffic patterns often cause severe performance degradation under cross-city deployment. Existing approaches based on domain adaptation, data augmentation, or synthetic data generation typically rely on labeled target data, city-specific annotations, or task-specific designs, limiting their scalability and effectiveness for holistic evaluation. In this paper, we introduce CityTransfer-Bench, a geographically disjoint benchmark for evaluating cross-city generalization across perception, segmentation, and planning, and propose CityGen, a diffusion-based generative framework that performs zero-label city adaptation via HD-map-conditioned synthesis guided by city-level visual prompts. Extensive experiments demonstrate that CityGen consistently improves cross-city robustness across multiple tasks, establishing a scalable and label-efficient foundation for generalizable autonomous driving.
