Content-aware image resizing in JavaScript

Re:Content-aware image resizing in JavaScript by ska on Friday April 16, 2021 @08:02PM (#26840375)

That's more related to a problem known as infilling. Generally throwing out information is a lot easier than generating it. You can do some statistical things by sampling other points of the image into newly created "gap" but it will probably look bad if fully automated, at least on big changes.

There's an obvious version of the algorithm in that direction. For one line "seam", it's easy enough, you just pull data from either side. But repeatedly applying it the more often your new "seams" end up next to something already estimated, the less real information there is - I suspect this becomes visually noticeable pretty fast.

[ Parent | on HN ]

Re:Content-aware image resizing in JavaScript by aeroheim on Friday April 16, 2021 @09:09PM (#26840770)

Are you referring to image inpainting? I think that's what it's usually called (please correct me if I'm wrong though!)

Although I'm not really familiar with traditional algorithms for inpainting, I've seen some ML research do some stuff with it that I found to be really impressive.

One demo that really stood out to me was the following: https://shihmengli.github.io/3D-Photo-Inpainting/

The algorithm they describe is able to inpaint pixels AND depth information from existing RGB-D photos, enabling images to be viewed in 3d space and be used with parallax effects. Really cool stuff!

[ Parent | on HN ]

Re:Content-aware image resizing in JavaScript by ska on Saturday April 17, 2021 @12:48PM (#26845629)

> Are you referring to image inpainting?

Yes, too late to edit but that's the more common name.

[ Parent | on HN ]