| license: apache-2.0 | |
| This is the model for the paper our paper [PIG-Nav: Key Insights for Pretrained Image-Goal Navigation Models](arxiv.org/abs/2507.17220). | |
| Description of this model: | |
| - This model (PIG-Nav) is pretrained on diverse indoor and outdoor navigation datasets. The model is trained by a total of 156K iterations with a batch size of 128. | |
| - Please follow our github repo for detailed use. |