lixiny / CPF

[ICCV 2021] CPF: Learning a Contact Potential Field to Model the Hand-Object Interaction
118 stars 17 forks source link

Some questions about PiQR code #10

Open lym29 opened 2 years ago

lym29 commented 2 years ago

In the contacthead.py, the three decoders have different input dimension. self.vertex_contact_decoder = PointNetDecodeModule(self._concat_feat_dim, 1) self.contact_region_decoder = PointNetDecodeModule(self._concat_feat_dim + 1, self.n_region) self.anchor_elasti_decoder = PointNetDecodeModule(self._concat_feat_dim + 17, self.n_anchor)

I am wondering if this part is used to predict selected anchor points within each subregion.

The classification of subregions is obtained by contact_region_decoder and then the anchor points are predicted by anchor_elasti_decoder, is it right ?

I am a little bit confused about it, because according to the paper, Anchor Elasticity (AE) represents the elasticities of the attractive springs. But in the code, the output of anchor_elasti_decoder has no relation to the elasticity parameter, I'm wondering if there's some part I've missed.

Sorry for any trouble caused and thanks for your help!

lixiny commented 6 months ago

> I am wondering if this part is used to predict selected anchor points within each subregion. Yes! this three modules are used to predict the VC (N_O, 1), CR (N_O, 17), and AE (N_O, N_anchor).

> the output of anchor_elasti_decoder has no relation to the elasticity parameter, The output of the anchor_elasti_decoder is a float numbers within the range: [0, 1). This scalar is treated as the elasticity parameter that helps to weight the squared distances between a hand vertex and an object vertex.

Best, Lixin