search

Lavreniuk / SPIdepth

Strengthened Pose Information for self-supervised monocular depth estimation. SPIdepth refines the pose network to improve depth prediction accuracy, achieving state-of-the-art results on benchmarks like KITTI, Cityscapes, and Make3D.
MIT License
30 stars 0 forks source link

Cityscape Fine-tuning #6

Open PoKoHA opened 1 week ago

PoKoHA commented 1 week ago

Dear @Lavreniuk,

Thank you for your grat work. May I inquire about the pre-trained KITTI model used for fine-tuning Cityscape?

Is it the 1024x320 KITTI model that utilizes ConvNeXt?

Your insights would be greatly appreciated.

Lavreniuk commented 1 week ago

hi @PoKoHA, thank you for your interest in our model! Yes, it is pre-trained KITTI model with ConvNeXt, you could download it using the links in the main of git repo.

PoKoHA commented 1 week ago

Thank you so much for your kind and quick reply.