search

zc-alexfan / hold

[CVPR 2024✨Highlight] Official repository for HOLD, the first method that jointly reconstructs articulated hands and objects from monocular videos without assuming a pre-scanned object template and 3D hand-object training data.
https://zc-alexfan.github.io/hold
MIT License
271 stars 7 forks source link

How to train from a single video #10

Closed Lyy-iiis closed 2 months ago

Lyy-iiis commented 2 months ago

I try to record a video myself and train the model. But except image of each frame, it also needs other files. I know I can use SAM to create mask, but can you give me a more detailed instruction on how your boxes.npy, data.npy and corres.txt comes from? Thank you!

Lyy-iiis commented 2 months ago

I find custom.md has a really detailed explain, Sorry to disturb.