search

DSaurus / Tensor4D

This is the official implementation of Tensor4D: Efficient Neural 4D Decomposition for High-fidelity Dynamic Reconstruction and Rendering.
MIT License
191 stars 4 forks source link

scale_mat in preprocess.py #5

Open ricshaw opened 1 year ago

ricshaw commented 1 year ago

Hi thanks for the great work! How do you compute the scale_mat in preprocess.py? How can we change this for our own data? Thanks

DSaurus commented 1 year ago

Hi,

In our implementation, scale_mat describes the center and size of the dynamic object. For example, If the bounding box of the object has a size of [2,3,4] and its center locates at [1,2,3], our scale_mat is set to

2/2 0 0 1
0 3/2 0 2
0 0 4/2 3

You can use visualhull to determine the bounding box of the object. In addition, scale_mat is to scale and translate the object from a roughly set bounding box to the range of [-1, -1, -1]~[1, 1, 1], and it does not need to be very precise.

tb2-sy commented 3 months ago

Hi,

In our implementation, scale_mat describes the center and size of the dynamic object. For example, If the bounding box of the object has a size of [2,3,4] and its center locates at [1,2,3], our scale_mat is set to

2/2 0 0 1
0 3/2 0 2
0 0 4/2 3

You can use visualhull to determine the bounding box of the object. In addition, scale_mat is to scale and translate the object from a roughly set bounding box to the range of [-1, -1, -1]~[1, 1, 1], and it does not need to be very precise.

36a348713bfcea7e423e575b6a1fe3ba Does such a rendering result mean that I need to adjust scale_mat?