Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2508.21102 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918132163018752 |
|---|---|
| author | Katsumata, Kei Iioka, Yui Hosomi, Naoki Misu, Teruhisa Yamada, Kentaro Sugiura, Komei |
| author_facet | Katsumata, Kei Iioka, Yui Hosomi, Naoki Misu, Teruhisa Yamada, Kentaro Sugiura, Komei |
| contents | 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/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_21102 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | GENNAV: Polygon Mask Generation for Generalized Referring Navigable Regions Katsumata, Kei Iioka, Yui Hosomi, Naoki Misu, Teruhisa Yamada, Kentaro Sugiura, Komei Computer Vision and Pattern Recognition Robotics 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/. |
| title | GENNAV: Polygon Mask Generation for Generalized Referring Navigable Regions |
| topic | Computer Vision and Pattern Recognition Robotics |
| url | https://arxiv.org/abs/2508.21102 |