This is interesting. Imagine that we have a series of multi-view wire structure (i.e., adding a time dimension), then we probably can project three different animations.
Thanks for sharing. Yes, what we found is that multiple input images often are not consistent with each other (i.e., no physical volume that can satisfy the constraints from all the views). We thus start with a set of consistent voxels and connect them so that the projections are as similar to the inputs as possible.
2 comments
[ 3.6 ms ] story [ 16.3 ms ] thread