Any methods to increase the generation speed? about deep-image-analogy HOT 9 OPEN

@gxlcliqi
Hi, you can train a decoder to make sure the feature maps is equivalent to those in the encoder. There is a reference : https://arxiv.org/abs/1705.08086 .

Yes, I think kd-tree can speed up patchmatch.

from deep-image-analogy.

1. You can use a decoder instead of LBFGS algorithm to deconvolve the feature maps. That would reduce much time.
2. If you do not care about the quality of results, you can generate only one direction's result . It will speed up if you get rid of one of the direction, such as AB or A'B'. Near 50 percent of the time cost can be saved.

from deep-image-analogy.

Thank you very much for your recommendation. I'll try these two methods to see if they can speed up.

from deep-image-analogy.

　I wan to know more about the speed corresponding with the resolution? Can you show us more results?

from deep-image-analogy.

1. Can you please kindly explain what kind of decoder to use, is it something like 'the pre-trained fast neural style' network?
2. Do you think if using the propagate-assist kd-tree to replace the patchmatch can improve the speed?

from deep-image-analogy.

@rozentill Thank you very much for the information, I will try it.

from deep-image-analogy.

@rozentill Hi, I don't understand why there must be two directions, I mean if there is only one direction how the result will be impacted? Thanks a lot.

from deep-image-analogy.

@gaoyangyiqiao Hi, the one direction also works. In both arXiv and SIGGRAPH versions of our paper, there are comparisons between one direction and two direction, the results using two direction would be better since the matching becomes more accurate.

from deep-image-analogy.

@rozentill Thanks a lot for answering. May I ask one more question, is there a python version to implement this paper?

from deep-image-analogy.