search

facebookresearch / InterHand2.6M

Official PyTorch implementation of "InterHand2.6M: A Dataset and Baseline for 3D Interacting Hand Pose Estimation from a Single RGB Image", ECCV 2020
Other
686 stars 91 forks source link

Result is bad! #143

Open herochen7372 opened 1 year ago

herochen7372 commented 1 year ago

input result_2d It is effective on the photos you provided, but the pictures I collected myself, even if the movements are similar, the effect is very poor. What is the reason, please.

mks0601 commented 1 year ago

Hi, this is expected as image appearances of interhand dataset is far from those of in-the-wild images. Please check my recent work for this https://github.com/facebookresearch/InterWild

Javacr commented 1 year ago

Hi, this is expected as image appearances of interhand dataset is far from those of in-the-wild images. Please check my recent work for this https://github.com/facebookresearch/InterWild

If I'm not mistaken, the reason is that @herochen7372 don not edit bbox, so the model cannot find joint in cropped image.

herochen7372 commented 1 year ago

Hi, this is expected as image appearances of interhand dataset is far from those of in-the-wild images. Please check my recent work for this https://github.com/facebookresearch/InterWild

If I'm not mistaken, the reason is that @herochen7372 don not edit bbox, so the model cannot find joint in cropped image.

Thanks for the reply, you're right.

mks0601 commented 8 months ago

You can use InterWild (https://github.com/facebookresearch/InterWild), which has its own hand detector, so you don't need to set bbox in advance.