WalkGPT: Grounded Vision-Language Conversation with Depth-Aware Segmentation for Pedestrian Navigation
Ensuring accessible pedestrian navigation requires reasoning about both semantic and spatial aspects of complex urban scenes, a challenge that existing Large Vision-Language Models (LVLMs) struggle to meet. Although these models can describe visual content, their lack of explicit grounding leads to object hallucinations and unreliable depth reasoning, limiting their usefulness for accessibility guidance. We introduce WalkGPT, a pixel-grounded LVLM for the new task of Grounded Navigation Guide, unifying language reasoning and segmentation within a single architecture for depth-aware accessibility guidance. Given a pedestrian-view image and a navigation query, WalkGPT generates a conversati...
| Authors | Rafi Ibn Sultan, Hui Zhu, Xiangyu Zhou et al. |
|---|---|
| Primary category | cs.CV |
| Published | 11 March 2026 |
| Last updated at source | 11 March 2026 |
Connected in the knowledge graph
- rafiibnsultan/PAVEDataset · cited by
Models and datasets referencing this paper
- rafiibnsultan/PAVEDataset
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.