Malte Prinzler

@Lemon-XQ and @XinWu98 I might have found the problem. I experienced the same error as you did when I trained a generalized MVSNeRF on my own dataset. I found the...

btw, if you use your own dataset, make sure to change the defaults for near and far in https://github.com/apchenstu/mvsnerf/blob/1fdf6487389d0872dade614b3cea61f7b099406e/utils.py#L112 they are not always adjusted according to your dataset specification!

this might solve the issue: https://github.com/apchenstu/mvsnerf/issues/12#issuecomment-1171424369

Have you been able to find a working solution? When I looked into the IMU data of euroc and data9_workbench, I found that the directions of gravity are not equal...

I have a question about your definition of `W_{sg}`. According to the xivo paper, the spatial frame is defined such that the gravity goes along the z-axis of the spatial...

Another possible explanation: the spatial frame coincides with the body frame during gravity initialization. Then everything is clear. Could someone please verify? Thanks

Yes that makes perfectly sense. Thank you very much for this clear explanation. I have one more question and even though it might not be directly connected to the EurocMav...

@UestcJay if you have a closer look at the camera .txt files of the training and evaluation set respectively, you'll find that for the training dataset, the camera intrinsics were...

any news on this? sounds like a very useful feature!

+1