Closed ttoinou closed 7 years ago
Our network is trained on modern photos, so there's a domain gap when applied to old movies. I think training your own network with old color movies is a great idea and can help bridge that gap. I would recommend starting from our network and fine-tuning on old movies.
Yes, temporal consistency would also make the results look nicer.
Thank you for your input, I'm first going to extract color frames from movies and documentaries. If I need ~500k iterations how many iter/images ? (not 1 I suppose)
I've extracted 12k frames from movies, now I need to create an LMDB file, do you think that tutorial would work http://deepdish.io/2015/04/28/creating-lmdb-in-python/ ? Sorry for the noob question
Hi ttoinou,
I'm also trying to use this engine for colorization on some historical images. Would have any interest in collaborating on this?
Hi, yes of course ! There's also another software for colorization : https://github.com/gustavla/autocolorize But I didn't succeed in installing it (yet)
My email : tit_toinou@hotmail.com
If someone wants to process an entire folder he can use my script : https://github.com/ttoinou/colorization/blob/master/color.py
Hi
Thanks for this script ! I tried your colorization (v2 with class rebalancing) on some frames from Man With a Movie Camera (Vertov, 1929) here are the results : https://drive.google.com/open?id=0B5-1OeNPsecwdTZ4dS0wUUhIaUU
Thanks in advance ! Antoine.