New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Why I get ghosting for own dataset? #80

Open

ZhenyanSun opened this issue Sep 14, 2024 · 1 comment

ZhenyanSun commented Sep 14, 2024 •

edited

Loading

Owner

tijiang13 commented Sep 15, 2024

Hi Zhenyan,

Judging from the output, I assume the estimated SMPL is not very accurate for the legs. A few questions:

did you run the preprocessing pipeline successfully? Normally by refining the SMPL with Openpose detection, the alignment will be good enough to get rid of this kind of noise.
Alternatively, you can try to replace ROMP with 4DHuman using the pipeline I shared in the other thread anim_nerf.npz #79

Best, Tianjian

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment