The closest I'm aware of is this: http://papers.nips.cc/paper/6650-toward-multimodal-image-to-... However, it requires rectified, segmented training data, unlike the above.
Wow--didn't expect my old paper to re-surface in 2018. Besides being a neat visualization, one remarkable thing (to me) is that this is one of the few computer vision tasks where the state-of-the-art is still the old…
The closest I'm aware of is this: http://papers.nips.cc/paper/6650-toward-multimodal-image-to-... However, it requires rectified, segmented training data, unlike the above.
Wow--didn't expect my old paper to re-surface in 2018. Besides being a neat visualization, one remarkable thing (to me) is that this is one of the few computer vision tasks where the state-of-the-art is still the old…