News for hackers. Stuff that matters.

A comment on High-Resolution Photorealistic Image Translation in Real-Time. Parent comment

Re:High-Resolution Photorealistic Image Translation in Real-... by danwills on Tuesday June 01, 2021 @03:36AM (#27351619)
This doesn't use wavelets afaics (they are not mentioned in the article), it uses something called 'Laplacian Pyramid'. That can be used separate a signal by frequency but seems to do the whole image at once. Looks to be the good old add-laplacian (ie 'blur') and subtract-from-the-original method (to get remaining high frequency).

I think wavelets usually have a limited extent in space (depending which basis shape you choose I guess).

Maybe they could make use of FFT for this separation, but it's probably hard to beat blur-and subtract for simplicity of implementation.

[ Parent | on HN ]
Re:High-Resolution Photorealistic Image Translation in Real-... by SimplyUnknown on Tuesday June 01, 2021 @05:53AM (#27352349)
Essentialy, you do the same thing as an FFT for separation. A gaussian blur is a low-pass filter, and functionally the same as selecting all frequency component within a radius r of the DC component (assuming the DC component is in the center of the image). The radius r depends on the width of the gaussian kernel.

The only difference could be in computational time (might be that the FFT is faster) and will be different if you use a different kind of blurring (i.e. non-gaussian such as selecting a square region in the frequency domain).

[ Parent | on HN ]
Re:High-Resolution Photorealistic Image Translation in Real-... by danwills on Tuesday June 01, 2021 @06:03AM (#27352419)
Agreed! And in cases where the convolution kernel (bokeh, but in frequency space) is something more complicated than gaussian, FFT can definitely be a very good option (kernel/bokeh-res can be near-ish to the res of the image-to-convolve, for example, and full-colour kernels/bokehs too).
[ Parent | on HN ]
Re:High-Resolution Photorealistic Image Translation in Real-... by dimatura on Tuesday June 01, 2021 @09:45AM (#27354374)
I don't have any quantitative evidence on computational performance of the FFT versus the typical laplacian pyramid technique, but I'd be surprised if FFT is faster. The classical laplacian pyramid -- developed in the 80s -- is really quite simple and fast. http://www.liralab.it/teaching/SINA_10/papers/burt-adelson19...
[ Parent | on HN ]