Map auto-regressor generates vectorized roads and buildings
MARS - A foundational map auto-regressor
Computer Vision and Pattern Recognition
Summary
Map generation can be hard because maps contain lots of complex shapes like roads and buildings, which are tricky for usual image-based methods to draw correctly. The authors created MARS, a new model that can draw entire maps made of roads and buildings as connected lines and shapes, all in one step. They trained MARS on a very large dataset of maps they collected, and it works as well or better than older multi-step methods. MARS also allows people to interact with it to correct maps as they are created.
What this means in practice
- •For mapping software developers: Create one-step map generation tools that produce vector roads and buildings from input data without separate segmentation and post-processing stages.
- •For geospatial data correction teams: Interactively refine and update vectorized maps with human-in-the-loop tools using the auto-regressive prediction framework.
Authors
Qi Zhang, Suvam Bag, Rupanjali Kukal, Lucas Thai, Jacob Kovarskiy, Mike Bianco, Xiaojie Guo, Raphael Tang, Mikael Figueroa, Rishi Madhok, Nikolaos Karianakis, Fuxun Yu
Abstract
Map generation tasks feature extensive non-structural vectorized data (e.g., points, polylines, and polygons) and thus pose significant challenges to common pixel-wise generative models. Conventional approaches use multiple stages, first segmenting these features at the pixel level and then performing vectorized post-processing, with errors and complexity compounding at each stage. Motivated by the recent success of auto-regressive language modeling, we propose the first map foundation model, named Map Auto-Regressor (MARS), that is capable of generating both multi-polyline road networks and polygon buildings in a unified manner. For training MARS, we collected to our knowledge the largest multi-class map extraction dataset totaling 3.4M examples, which we call MAP-3M. Across four road and building datasets, MARS outperforms or matches the performance of multistage baselines. Additionally, we develop a "Chat with MARS" capability that enables interactive human-in-the-loop map generation and correction, supported by the auto-regressive nature of our end-to-end approach. We release our MAP-3M dataset and project demo page at (1) https://huggingface.co/datasets/bag-lab/MAP-3M and (2) https://huggingface.co/spaces/bag-lab/MARS, respectively.