Slashdot Mirror
Japan Researchers Develop Automated Technique For Anime Colorization Using Deep Learning (brightsurf.com)
Japanese researchers have developed a technique for automatic colorization in anime production. "To promote efficiency and automation in anime production, the research team focused on the possibility of automating the colorization of trace images in the finishing process of anime production," reports Brightsurf. "By integrating the anime production technology and know-how of IMAGICA GROUP and OLM Digital with the machine learning, computer graphics and vision technology of NAIST, the research team succeeded in developing the world's first technique for automatic colorization of Japanese anime production." From the report: After the trace image cleaning in a pre-processing step, automatic colorization is performed according to the color script of the character using a deep learning-based image segmentation algorithm. The colorization result is refined in a post-process step using voting techniques for each closed region. This technique will be presented at SIGGRAPH ASIA 2018, an international conference on computer graphics and interactive techniques, to be held in Tokyo, Japan on Dec. 4-7. While this technique is still in the preliminary research stage, the research team will further improve its accuracy and validate it in production within the anime production studio. The product of this will be available for commercialization from 2020.
How many artists will get to start their own work rather than filling in frames for others?
Domestic spying is now "Benign Information Gathering"
Once you start to get 3d assets and computerised stuff in anime it loses that look which gives it that x factor. It's too clean and looks wrong. IMO at least.
Wanna buy a shirt?
https://www.redbubble.com/people/stealthfinger/shop?asc=u
Why is it that you NEVER hear of Africans EVER inventing something like this?
Could it possibly have something to do with race and IQ?
Cue irrational Slashdotters trying to deny reality because it isn't 'politically correct'...
What's the point of a short text article about graphics without adding any pictures/video clip as demonstration ?
I suppose an article like that would have samples showing the technique in action, but I guess it's asking too much
numbers c"ontinue
To whomever wrote this: thank you for calling this Deep Learning instead of going "OMG AI".
Interesting how it will perform on it :)
This is the type of task that can really benefit from neural networks and deep learning, tasks that are somewhat repetitive and time consuming and follow a certain pattern and set of rules. Funny how you can always count on the Japanese for optimizing current technology, it's really what makes them formidable
Too bad anime plots seem computer generated these days.
“Common sense is not so common.” — Voltaire
Trump finally did it!
In related news, there's a program called "waifu2x" that uses deep learning and neural networks (and CUDA, if you have an NVIDIA graphics card...highly recommended, there's a ~4x speed boost on my machine) to automatically scale up ("super-resolution") and de-noise anime art: https://github.com/nagadomi/wa...
For Windows users, use this version: https://github.com/lltcggie/wa...
RTFA and there's nothing there.... just "we can do this" but no pics (likely because they're going to announce the technique formally in Dec). I expect that this will look more or less something like the cell-shaded early CGI animation.
Obviously, this is about "optimizing" the drudgework of colorizing, meaning the teams of sub-artists on productions will just be a little smaller.
I guess everything depends on how persuasive this looks; it could be cool and seems like a relatively low-hanging fruit for automation of the process. Even if it looks shitty, the consumer audience has such low demands that they've (I guess) come to accept the already-significantly-automated interpolation and heavy-trace processes common to the cheaper anime/cartoons.
-Styopa
How much modern Anime is CGI. You can only tell when they fall down (like making a character too detailed so the cell shading ends up with artifacts instead of large flat segments that don't change much during a scene.)
Everything I have watched this year is CGI, and most either uses 'grain' over the CGI, or just leaves it in. Especially bad are the Americanized CGI Animes, like new Berserk, Fist of the North Star Regenesis, Baki (Netflix's adult oriented stab at these), Goblin Slayer (which I can't recommend enough, adult lots of D&D references but a flavor of its own.)
For anyone who wants to complain, this goes all the way back to Akira and composited work has been going on at least since Techi Muyo: GXP!
Anime as you knew it is and has been dead for 35 years. A few dinosaurs stayed around after that, but production turnaround and budgets haven't resulted in material that wasn't computer assisted in at least 12 years.
I bet we will see some weird mistake, like pink hair.
I've waited years for the second seasons for Shingeki no Kyojin and One Punch Man. Get on it, Japan. I'm counting on you to learn Japanese.
There are a couple ones online if you want to try them. Style 2 Paints will do automatic colorization, and Make Girls Moe will autogenerate anime faces.
Once you start to get 3d assets and computerised stuff in anime it loses that look which gives it that x factor.
Anime loses it's great and compelling stories, character development, excellent voice acting, and overall joy to watch because a computer was involved in drawing?