DongyangHuLi

Wonderful code! Thanks for your contribution! I wonder if batch size has a large effect on model performance? Or other factors? Looking for your reply!

About focal_scale

1

Hi, thank you for nice work! I'm confused about the 'focal_scale'. Why do we need to do this: https://github.com/weiyithu/SurroundDepth/blob/22dfecfe8fca62a38d0f682ff7bf65b41aba3cac/runer.py#L382-L383

About training

1

Can I train as a whole at once instead of in stages？

Question about the image size

1

Thanks for sharing the code! I'm confused about the size of the image input from the diffusion model. In the code why limit the height and width of the image...

Hi, your great work is impressing! But I'm a little confused about the warp loss and Validity masks: 1."our warping-based loss such that every valid patch in the reference image...

Hi~ kamse, Thank you for your excellent work! It's very inspiring to me. Could you provide your training code?