We thank the reviewers for their helpful suggestions

CV and AI have developed a culture of idolizing and wanting to be idolized. This happens in other fields too, but it gains momentum as more of the people rising to the top become increasingly arrogant, boastful, and lacking in humility - it's a self-reinforcing feedback loop.

Reviewer’s evaluation of your argument

gradient descent

You do your best, and you move forward. Regret is a counterfactual labyrinth I choose to stay out of it.

Though not widely appreciated, the Traveling Salesman problem was solved by this guy in 1961.

'This paper contains much that is new, and true. But that which is new is not true; and that which is true is not new'

“We achieve state of the art on standard benchmarks”

How can you move an image by a tiny (sub-pixel) amount? It's easy if you know about optical flow!

To move an image by a sub-pixel amount we can use the classic brightness constancy idea from optical flow.

Say we start with an image f(x,y) and want to move by an amount (δx,δy)

It was almost exactly 10 years ago, on April 16, 2014 that Google first released the Google Camera App. In that time, we've made huge strides in computational imaging, many of which leading the industry.

Nice article in Inverse about this history:
inverse.com/tech/google-ca…

Congratulations to Hossein Talebi & Peyman Milanfar for winning the IEEE Signal Processing Society's Best Paper Award for their paper titled 'NIMA: Neural Image Assessment'! #ICASSP2024 signalprocessingsociety.org/community-invo…

Thanks to IEEE Signal Processing Society for this great recognition, and congratulations to my co-author Hossein Talebi who deserves all the credit.

Paper: ieeexplore.ieee.org/document/83528…

everybody in AI chasing the same idea

everybody in AI chasing the same idea

ladies and gentlemen, the weekend

This is pointless and contributes only to worsening hype about AI, and the college admissions rat race.