Decensoring Hentai with Deep Neural Networks
1–10 of 73 posts
Re: Decensoring Hentai with Deep Neural Networks
#2Gotta give them some credit, that is a brilliant name.
Re: Decensoring Hentai with Deep Neural Networks
#3Are there any more examples? Removing a few lines doesn't seem that impressive and can be done with the PhotoShop pattern tool without any fancy neural net.
Re: Decensoring Hentai with Deep Neural Networks
#4Are there any more examples? Removing a few lines doesn't seem that impressive and can be done with the PhotoShop pattern tool without any fancy neural net.
There are examples posted on 4chan's /h/ board, that is to say, people using it for its intended purpose rather than only with examples, but I'm at work so I can't really browse it at the moment (and the threads are ephemeral anyway, unless you use an archive site).
Re: Decensoring Hentai with Deep Neural Networks
#5I believe "Image Inpainting for Irregular Holes Using Partial Convolutions" has been superseded by "Free-Form Image Inpainting with Gated Convolution", especially for interactive use cases?
https://arxiv.org/pdf/1806.03589.pdf
http://jiahuiyu.com/deepfill2/
I think the most interesting part of this project would be generating the dataset. That is a lot of manual redrawing of vaginas/penises. Or the reverse, where you find already decensored stuff and add realistic censorship yourself. Either way, a lot of time will be spent tagging genitals to build a large enough dataset to make NN techniques work...
Re: Decensoring Hentai with Deep Neural Networks
#6Are there any more examples? Removing a few lines doesn't seem that impressive and can be done with the PhotoShop pattern tool without any fancy neural net.
More examples and commentary found here: https://boards.4chan.org/g/thread/68220714#p68220714
Edit: should have mentioned NSFW
Re: Decensoring Hentai with Deep Neural Networks
#7Are there any more examples? Removing a few lines doesn't seem that impressive and can be done with the PhotoShop pattern tool without any fancy neural net.
There are examples posted on 4chan's /h/ board, that is to say, people using it for its intended purpose rather than only with examples, but I'm at work so I can't really browse it at the moment (and the threads are ephemeral anyway, unless you use an archive site).
some threads are archived, your sibling for example
Re: Decensoring Hentai with Deep Neural Networks
#8I believe "Image Inpainting for Irregular Holes Using Partial Convolutions" has been superseded by "Free-Form Image Inpainting with Gated Convolution", especially for interactive use cases? https://arxiv.org/pdf/1806.03589.pdf http://jiahuiyu.com/deepfill2/ I think the most interesting part of this project would be generating the dataset. That is a lot of manual redrawing of vaginas/penises. Or the reverse, where you…
It's not clear to me that you'd actually need to manually label individual images for training. The work of detecting and marking the censored regions is left to the user, so the model just needs to be good at inpainting. There are probably enough specialized sites to get a decently-sized training set with little effort beyond writing a crawler.
Re: Decensoring Hentai with Deep Neural Networks
#9I believe "Image Inpainting for Irregular Holes Using Partial Convolutions" has been superseded by "Free-Form Image Inpainting with Gated Convolution", especially for interactive use cases? https://arxiv.org/pdf/1806.03589.pdf http://jiahuiyu.com/deepfill2/ I think the most interesting part of this project would be generating the dataset. That is a lot of manual redrawing of vaginas/penises. Or the reverse, where you…
There's tens of thousands of manually decensored manga, you could download and compare them to original to identify censored regions and use as training I suppose.
Re: Decensoring Hentai with Deep Neural Networks
#10I believe "Image Inpainting for Irregular Holes Using Partial Convolutions" has been superseded by "Free-Form Image Inpainting with Gated Convolution", especially for interactive use cases? https://arxiv.org/pdf/1806.03589.pdf http://jiahuiyu.com/deepfill2/ I think the most interesting part of this project would be generating the dataset. That is a lot of manual redrawing of vaginas/penises. Or the reverse, where you…
It's not clear to me that you'd actually need to manually label individual images for training. The work of detecting and marking the censored regions is left to the user, so the model just needs to be good at inpainting. There are probably enough specialized sites to get a decently-sized training set with little effort beyond writing a crawler.
You could be right, I don't know. Maybe the authors can tell us about their experience.
My intuition is that the dataset will be too imbalanced to learn anything useful. Even if you crawl only decensored images, the area you truly care about inpainting is still pretty small. If you don't focus on it somehow, it might learn how to inpaint anime-style geometry correctly (from the rest of the image) but produce "barbie doll" style anatomy.