search

jzhzhang / 3DAwareNav

[CVPR 2023] We propose a framework for the challenging 3D-aware ObjectNav based on two straightforward sub-policies. The two sub-polices, namely corner-guided exploration policy and category-aware identification policy, simultaneously perform by utilizing online fused 3D points as observation.
MIT License
57 stars 3 forks source link

model and evaluation about Gibson dataset #6

Closed zenght closed 9 months ago

zenght commented 11 months ago

Thank you for sharing. I would like to know if it is possible to provide the model trained on the Gibson data set and the eval code.

jzhzhang commented 11 months ago

We do not have plans to update the Gibson code in this repository. Instead, you can directly utilize the 2D semantic predictor from https://github.com/devendrachaplot/Object-Goal-Navigation and train our exploration and identification policies.