NeuralRecon
NeuralRecon copied to clipboard
Difference between voxel grid and fragment volume?
The fragment volume is defined as the cubic volume that encloses the view frustums (with each frustum having a max distance). Thus, this volume can change based on the specific view frustums.
But the voxel grid appears to have a fixed size: e.g. 96 voxels in each dimension with a voxel size of 0.04 m.
Is the voxel grid aligned with the min corner of the fragment volume, but with a potentially different max corner?