Ni_ZY

Results 7 comments of Ni_ZY

Question about the result of online adaptation with "L2AWad"

And the image shape of Synthia is scaled to half resolution: [380, 640]

Question about the result of online adaptation with "L2AWad"

Hi, thank you very much for your reply. Since I only want to test the effect of confidence weight, I only use this meta-training strategie: "L2AWad", and I have not...

Question about the result of online adaptation with "L2AWad"

Hello @AlessioTonioni ， I thought about it for a while and thought this phenomenon might be normal. I randomly read 100 disparity ground-truth maps from the datasets synthia, KITTI, and...

Question about the pretrained weights

Well, thanks for your answer and code! @AlessioTonioni In order to train the weights of L2A+Wad, there are still several problems, as follows: 1. Is the Synthia dataset you used...

Question about the pretrained weights

All right, I got it. Thanks a lot!

Ground-truth of raw data in KITTI dataset

Ah, I found it, thank you very much! @mattpoggi

Question about the result of online adaptation with "L2AWad"

@peiran88 In my impression, I modified the configuration and retried several times, but it was the same result. You can refer to my comments above. I think the main reason...