I've also been wondering if there is something similar to Content Aware Fill that can help process old 4:3 cartoons to 16:9.
A lot of the really old cartoons would use a background art image and would pan over it with the characters dong stuff to create a sense of motion. Sometimes the characters would move over a still background image but the 'camera's would zoom in.
Something that could extract the full size background image to apply it to the frames to enlarge the aspect ratio could go a long way toward revitalizing a lot of older cartoons. Especially fit could fill in any gaps using the opensource equivilent of Content Aware Fill (is there an FOSS equal?)
I've been trying to get my kids into Space Ghost Coast to Coast, Home Movies, Sealab 2021, the Simpsons, etc. If the video is wide screen they try it and enjoy it. If it's 4:3 they barely give it a chance because it's "too old"
”Adobe Systems acquired a non-exclusive license to seam carving technology from MERL, and implemented it as a feature in Photoshop CS4, where it is called Content Aware Scaling. As the license is non-exclusive, other popular computer graphics applications, among which are GIMP, digiKam, ImageMagick, as well as some stand-alone programs, among which are iResizer, also have implementations of this technique, some of which are released as free and open source software”
Seam carving removes stuff, but the principle is the same. The Gimp plug-in is http://www.logarithmic.net/pfh/resynthesizer, and apparently also can do the filling-in. I haven’t used it, so I don’t know how good it is.
My only experience with Photoshop is through memes; is Content Aware Fill the same as Content Aware Scaling? I thought the former tried to guess what was "behind" something you removed, while the latter just moves the existing pixels around by guessing which ones need to stay together when you resize something.
See the PatchMatch research project and associated papers[1] for more detail. They are different tools in presentation and implementation within Photoshop but are based on similar concepts of randomized correspondence.
”We propose a simple image operator, we term seam-carving, that can change the size of an image by gracefully carving-out OR INSERTING pixels in different parts of the image”
That paper (which I think is the paper introducing the seam carving technique) also has examples of widening pictures.
A lot of the really old cartoons would use a background art image and would pan over it with the characters dong stuff to create a sense of motion. Sometimes the characters would move over a still background image but the 'camera's would zoom in.
Something that could extract the full size background image to apply it to the frames to enlarge the aspect ratio could go a long way toward revitalizing a lot of older cartoons. Especially fit could fill in any gaps using the opensource equivilent of Content Aware Fill (is there an FOSS equal?)
I've been trying to get my kids into Space Ghost Coast to Coast, Home Movies, Sealab 2021, the Simpsons, etc. If the video is wide screen they try it and enjoy it. If it's 4:3 they barely give it a chance because it's "too old"