Abstract:We introduce Goal-Conditioned Visual Navigation Instruction Generation (GoViG), a new task that aims to generate contextually coherent navigation instructions solely from egocentric visual observations of initial and goal states. Unlike prior work relying on structured inputs, such as semantic annotations or environmental maps, GoViG exclusively leverages raw egocentric visual data, improving adaptability to unseen and unstructured environments. Our method addresses this task by decomposing it into two interconnected subtasks: (1) navigation visualization, predicting intermediate visual states bridging the initial and goal views; and (2) instruction generation, synthesizing coherent instructions grounded in observed and anticipated visuals. Both subtasks are integrated within an autoregressive multimodal LLM trained with tailored objectives to ensure spatial accuracy and linguistic clarity. Furthermore, we introduce two multimodal reasoning strategies, one-pass and interleaved reasoning, to mimic incremental human navigation cognition. To comprehensively evaluate our method, we propose the R2R-Goal dataset, combining diverse synthetic and real-world trajectories. Empirical results demonstrate significant performance improvements over state-of-the-art methods in BLEU-4 and CIDEr scores along with robust cross-domain generalization.
| Comments: | Accepted to ACL 2026 Findings. 22 pages, 12 figures, Code: this https URL |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2508.09547 [cs.CV] |
| (or arXiv:2508.09547v2 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2508.09547 arXiv-issued DOI via DataCite |
Submission history
From: Zhi-Qi Cheng [view email]
[v1]
Wed, 13 Aug 2025 07:05:17 UTC (3,909 KB)
[v2]
Wed, 29 Apr 2026 01:36:59 UTC (4,089 KB)