Closed charley077 closed 8 months ago
Hi,
Thanks for your interest.
With the current implementation, the function is not differentiable with respect to w0
, w1
and w2
. Moreover, for our use case, we use need only the forward pass through this layer and do not use the differentiability with respect to min_dis
either.
More generally, making the uvd conversion truly differentiable is non-trivial, and worth investigating.
Hope that answers your question.
Hi,
Thanks for your interest.
With the current implementation, the function is not differentiable with respect to
w0
,w1
andw2
. Moreover, for our use case, we use need only the forward pass through this layer and do not use the differentiability with respect tomin_dis
either.More generally, making the uvd conversion truly differentiable is non-trivial, and worth investigating.
Hope that answers your question.
It really helps. Thanks for your reply!
Hi, thanks for the great work! I'm interested in the 'uvh' representation which makes the model faster. I have one question in the process to get 'uvh'. In the following function: https://github.com/amundra15/livehand/blob/7ba95ce657f97924e9a49dc672ab4bd9ea29a0ff/input_encoder.py#L88 I notice that you only calculated the derivative of
pts
with respect tomin_dis
. I want to know ifpts
is differentiable with respect tow0
,w1
andw2
? If so, how can I calculate the derivative ofpts
with respect to the barycentric weights?