How many frames do you used?

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

303 stars 7 forks source link

How many frames do you used? #2

Closed EAST-J closed 11 months ago

EAST-J commented 11 months ago

Hi, your work is impressive. I'm curious about the number of frames from the input video that you used for training?

zc-alexfan commented 11 months ago

Hi, thanks for your interest. Most videos, we use around 200-300 frames to train.