Closed longbowzhang closed 2 years ago
Hi @longbowzhang,
Sorry for the very late reply!
Hi @lzqsd,
Thanks a lot for your reply.
But I still fail to figure out the setup of the coordinate system of hemisphere based on the following code.
https://github.com/lzqsd/InverseRenderingOfIndoorScene/blob/64baec4a03498f3ab7b60d98ed79be27ebf78e27/models.py#L480
normalPred
will be the z-axis, and camy
will the y-axis, right? If so, the x-axis (i.e., camx
) should be the cross product of camy
and normalPred
. But why reversing the result of cross product by adding a minus sign -
after normalization?
During inference, the input should be a gamma-corrected LDR image, right? But during training, a HDR image is used as input. I am just wondering how to deal with this mismatch?
Looking forward to your reply!
Hi @longbowzhang ,
As for the first question, it is just how we define the coordinate system. There is no specific reasons for that.
We actually clip the HDR image into the range of 0 to 1 during training, to make sure that training and testing can match.
Hi @lzqsd Very amazing work which inspires me quite a lot! But I still have several questions, and I hope you could kindly clarify them.
The x and y axis of the coordinate system of hemisphere used in illumination. Why use L1 (
p=1
) normalization instead of L2, and, why getcamx
by reversing the cross product ofcamy
andnormalPred
? https://github.com/lzqsd/InverseRenderingOfIndoorScene/blob/eeac1e960f0ba6be98afcbfcaa39c23e2dfcd4f1/models.py#L480I have also a general question about the linear space and gamma space. The input image I is gamma-corrected LDR, and the output of the render equation is the radiance in linear space. Thus I am wondering whether it makes sense to compute the render loss, although with a scale factor, as shown in Eqn. (7) in the paper?
Looking forward to your reply, and thanks a lot in advance!