KITTI360 fisheye experiment

[dialogueeeeee]

Hello,

I would like to express my appreciation for your impressive work.

I am currently attempting to replicate the results of the KITTI360 fisheye experiment as described in your paper and provided in the repository. However, I am encountering some difficulties in achieving the reported results.

1. I trained the model using the original code and settings for 20 epochs. The results I obtained were different from those reported in the paper.

2. To address this, I increased the batch size and extended the training to 50 epochs. Even with these adjustments, the results remain not good.

Thank you for your time and assistance, again.

[Owen-Liuyuxuan]

Thanks for your attention to the work. I have not been training fisheye images for a while. It may take some days to reproduce.

[Owen-Liuyuxuan]

Did you resize your image before training, if so you may need to pay attention to the calibration files

[Owen-Liuyuxuan]

When I start the training from scratch with pre-resizing images, I get reconstruction loss at about 0.08+. If you constantly observing reconstruction loss larger than 1, there could be bugs somewhere.