[derefr]

A related idea would be “image summarization”, i.e. an (as-yet hypothetical) technique for generating an image that’s an “icon” of a larger image. In the same sense of “icon” as the one visual designers are trained to create: one where both large-scale structure (shape+color) and fine-scale structure (texture) are preserved, while “redundant” detail is sacrificed, in order of least to most important for visual recognition by a human or image-classifier model. You could also call this a type of psycho-visual compression, in the same vein as chroma subsampling.

Simply resampling an image smaller keeps the large-scale structure (the shape and color), but loses the fine-scale structure (texture.) That’s why we don’t just resample photos down to 32x32 and use them as icons :)

Seam Carving (whether parallel or not) does the opposite: it preserves the fine-scale structure (texture) but distorts the large-scale structure (shape.)

But not always! The amount of shape distortion in Seam Carving is worst case O(N) with the number of seams deleted, but best-case o(1). It depends on the algorithm’s choices of seam.

Regular iterative Seam Carving, as described by its original paper, isn’t stateful-enough to be able to minimize any whole-image quality (like loss of large structure.) So it’s no surprise it hasn’t been used for something like this.

But parallel Seam Carving might just be the ticket for this problem. A model could be trained to select an optimal set of seams that work together to minimize the large-structure deformation of the image (i.e. the image’s lower-band difference in frequency-space), while also individually being low-entropy seams from the Seam Carving algorithm’s perspective.

Anyone want to take a crack at this?