We focus on the task of identifying the location of target regions from a natural language instruction and a front camera image captured by a mobility. This task is challenging because it requires both existence prediction and segmentation, particularly for stuff-type target regions with ambiguous boundaries. Existing methods often underperform in handling stuff-type target regions, in addition to absent or multiple targets. To overcome these limitations, we propose GENNAV, which predicts target existence and generates segmentation masks for multiple stuff-type target regions. To evaluate GENNAV, we constructed a novel benchmark called GRiN-Drive, which includes three distinct types of samples: no-target, single-target, and multi-target. GENNAV achieved superior performance over baseline methods on standard evaluation metrics. Furthermore, we conducted real-world experiments with four automobiles operated in five geographically distinct urban areas to validate its zero-shot transfer performance. In these experiments, GENNAV outperformed baseline methods and demonstrated its robustness across diverse real-world environments. The project page is available at https://gennav.vercel.app/.
@article{arxiv.2508.21102,
title = {GENNAV: Polygon Mask Generation for Generalized Referring Navigable Regions},
author = {Kei Katsumata and Yui Iioka and Naoki Hosomi and Teruhisa Misu and Kentaro Yamada and Komei Sugiura},
journal= {arXiv preprint arXiv:2508.21102},
year = {2025}
}