Live data from Hacker News

Segmenting comic book frames

vrroom.github.io

21–30 of 53 posts

Re: Segmenting comic book frames

#23
Awesome stuff! We're also working on comic segmentation @ https://toona.io and other stuff for motion comic generation. The synthetic dataset approaches are really interesting, I'm curious if you could use an algorithm like https://en.wikipedia.org/wiki/Flood_fill to aid in segmentation (especially for manga).

Re: Segmenting comic book frames

#24
Segmenting panels is a graphic design element of storytelling that's part of the artist's job. Doing it programmatically ignores its actual nature in storytelling - establishing the amount and direction of the story beats, helping the reader understand the right reading order, and establishing the important elements on the page (Which beat is the most important, etc).

It's an interesting tech but giving such an important creative job to a computer instead of an artist is a bad idea for any comic artist who cares about their work.

Re: Segmenting comic book frames

#25

Segmenting panels is a graphic design element of storytelling that's part of the artist's job. Doing it programmatically ignores its actual nature in storytelling - establishing the amount and direction of the story beats, helping the reader understand the right reading order, and establishing the important elements on the page (Which beat is the most important, etc). It's an interesting tech but giving such an impor…

Sure, but this is an article about detecting the edges of the panels

Re: Segmenting comic book frames

#26
post #23

Awesome stuff! We're also working on comic segmentation @ https://toona.io and other stuff for motion comic generation. The synthetic dataset approaches are really interesting, I'm curious if you could use an algorithm like https://en.wikipedia.org/wiki/Flood_fill to aid in segmentation (especially for manga).

The original blog post by Max Halford (https://maxhalford.github.io/blog/comic-book-panel-segmentat...) does exactly that. I love his approach because, unlike mine, it is simple, yet it goes a long way. I'd encourage you to check it out.

Can you explain what you mean by motion comic generation? Sounds interesting!

Re: Segmenting comic book frames

#27

I always thought a fun side gig (or even volunteer opportunity) would be defining panel areas for digital comics. Both because I'd get to read a lot of comics, and because a lot of comics I read are frustratingly bad at it, and it makes it much harder to enjoy them. Well, there goes AI taking our jerbs.

The author here. I would just like to say that this project is definitely work-in-progress and the AI elements often fail miserably.

As amazing as recent AI progress has been, we do overrate it a lot (I'm including myself in that).

Re: Segmenting comic book frames

#29

Next AI challenge: try to infer the intended panel reading sequence, and the flow of speech bubbles/narrative. Would potentially be a useful augmentation to a digital comic book reader, refocusing from panel to panel in sequence. Not to mention making comic book content more accessible.

Files in ACBF format include panel metadata. So there should be lots of training data.

- https://launchpad.net/acbf

Re: Segmenting comic book frames

#30
post #26
post #23

Awesome stuff! We're also working on comic segmentation @ https://toona.io and other stuff for motion comic generation. The synthetic dataset approaches are really interesting, I'm curious if you could use an algorithm like https://en.wikipedia.org/wiki/Flood_fill to aid in segmentation (especially for manga).

The original blog post by Max Halford ( https://maxhalford.github.io/blog/comic-book-panel-segmentat... ) does exactly that. I love his approach because, unlike mine, it is simple, yet it goes a long way. I'd encourage you to check it out. Can you explain what you mean by motion comic generation? Sounds interesting!

Oh wow I'll check that out! We're basically working on tools for turning normal comics into semi-animated versions with things like puppet animation (similar to live 2d style), and stable diffusion models. A lot of the work for traditional approaches is segmentation and in painting, so that's what we're working on now, but we're also making tools for colorization, effects, and controllable animations!
Post reply on HN