search

nex-mpi / nex-code

Code release for NeX: Real-time View Synthesis with Neural Basis Expansion
MIT License
594 stars 73 forks source link

Question about viewing direction, basis function, gpu memory #51

Closed bring728 closed 2 years ago

bring728 commented 2 years ago

All 3d points along one ray have the same viewing direction. So when rendering, isn't it enough to input only one viewing direction rather than input all duplicate viewing directions into the basis function?

Below is the result I checked by myself. out2 is the basis function value. image

As you can see, all 32 values have the same value of 0.1176. Since the input is the same, the output is of course the same. My question is, do I really need to waste network memory? Instead of having 32 inputs, isn't it enough to have just 1 input?

pureexe commented 2 years ago

The viewing direction is the same as long the ray. The same viewing direction also produces the same basis value.

Our code is not focusing on performance. feel free to improve it.

bring728 commented 2 years ago

i See. Thank you for answer. I was wondering if there might be another reason.