humannerf icon indicating copy to clipboard operation
humannerf copied to clipboard

Published 20 hours ago • verified publisher icon chungyiweng

Getting weird results when training with custom data

Open qzane opened this issue 2 years ago • 6 comments

prog_025000 I got this weird result, is it normal or did I do any wrong? I validate my camera parameters using cv2.projectPoints and they seems to be correct. Also, I have another dataset in which I got the body pose using EasyMocap, can I just use the 'pose' and 'Rh' data from them (I also checked the code in prepare_dataset.py and find that you actually don't need 'Th', right?

qzane avatar Oct 13 '22 16:10 qzane

@qzane,

Even I am getting weird results for my dataset when training. Did you generate your smpl values from ROMP/VIBE?

Maybe its the camera values or something wrong. If you solved it, it would be great if you can provide some information on this.

I will be waiting for your response

prog_005000

Dipankar1997161 avatar Jun 09 '23 22:06 Dipankar1997161

LOL, it seems I was not the only one getting this: prog_040000

leviome avatar Jul 19 '23 14:07 leviome

I am experiencing something similar with the results form 4D Humans. Has anyone solved this issue?

StephenYangjz avatar Sep 03 '23 15:09 StephenYangjz

I am experiencing something similar with the results form 4D Humans. Has anyone solved this issue?

That's because the projection of sampling rays isn't 100% accurate. So make sure you have the correct camera values.

Dipankar1997161 avatar Sep 03 '23 16:09 Dipankar1997161

I am experiencing something similar with the results form 4D Humans. Has anyone solved this issue?

That's because the projection of sampling rays isn't 100% accurate. So make sure you have the correct camera values.

I ran 4d humans on mocap just to verify, and I even tried to substitute the cam in/extrinsics by the mocap dataset gt. It still gave me similar results...

StephenYangjz avatar Sep 03 '23 16:09 StephenYangjz

I am experiencing something similar with the results form 4D Humans. Has anyone solved this issue?

That's because the projection of sampling rays isn't 100% accurate. So make sure you have the correct camera values.

I ran 4d humans on mocap just to verify, and I even tried to substitute the cam in/extrinsics by the mocap dataset gt. It still gave me similar results...

What do you mean by running mocap on it? Did you mean Easymocap?

Dipankar1997161 avatar Sep 03 '23 20:09 Dipankar1997161