luanfujun/deep-photo-styletransfer

How are you doing the segmentation?

nandexsp opened this issue · 1 comments

Hi,

how are you doing the segmentation? I tried to use selective search but the results are poors and doesnt work as I want. :(

Any Ideas?

For automatic segmentation you can something like this one: https://github.com/CSAILVision/sceneparsing
or this one: http://www.cs.unc.edu/~jtighe/Papers/ECCV10/

For the masks we provided in this repository, they are generated using photoshop quick selection tool :-)