I read an image-based 3D-reconstruction paper, and there is a paragraph as following:
Volumetric representations, which have been extensively adopted in early deep leaning-based 3D reconstruction techniques, allow the parametrization of 3D shapes using regular voxel grids. As such, 2D convolutions used in image analysis can be easily extended to 3D. They are, however, very expensive in terms of memory requirements, and only a few techniques can achieve sub-voxel accuracy.
So what's the meaning of sub-voxel?
