About the 2D segmentor

Open monoavatar opened this issue 2 years ago • 1 comments

Hi, thanks for your nice work!

I'm interested in the 2D segmentor that you used in CAMA. The paper mentions that you use Mask2Former to get road and lane segmentation masks. May I ask which specific model & results are ued in CAMA (Mapillary Vistas Model and Semantic Segmentation results? or the Panoptic Segmentation results?)

Looking forward to your reply!

Oct 07 '23 11:10 monoavatar

Thanks for the interets, Mask2Former trained on Mapillary is good, no need for panoptic segmentation.

Oct 13 '23 09:10 manymuch