News for hackers. Stuff that matters.

A comment on NPGA: Neural Parametric Gaussian Avatars – high-fidelity digital faces.

Re:NPGA: Neural Parametric Gaussian Avatars – high-fidelity ... by azinman2 on Friday May 31, 2024 @01:33AM (#40531823)
Given the now clear abuse potential (and other issues surrounding AI generally), why do papers like this discuss the motivation as if it’s a for sure requirement to do such work?

“The creation of high-fidelity, digital versions of human heads is an important stepping stone in the process of further integrating virtual components into our everyday lives.”

It’s not clear to me that’s a desirable outcome.

[ Parent | on HN ]
Re:NPGA: Neural Parametric Gaussian Avatars – high-fidelity ... by techbro92 on Friday May 31, 2024 @01:40AM (#40531849)
It is kind of a requirement. Scientific papers will typically describe the motivation for a work to start the introduction. The real motivation of course is “I need to publish something”.
[ Parent | on HN ]
Re:NPGA: Neural Parametric Gaussian Avatars – high-fidelity ... by throwaway1105q on Friday May 31, 2024 @02:16AM (#40532031)
The real motivation is "I want to research this field", publishing is part of the way. Nobody is doing research "to publish something", there are much simpler fields to enter if that was the motivation.
[ Parent | on HN ]
Re:NPGA: Neural Parametric Gaussian Avatars – high-fidelity ... by superb_dev on Friday May 31, 2024 @05:32AM (#40533001)
If you decide to research in $field, then you’ll typically need to keep publishing papers to keep your job
[ Parent | on HN ]
Re:NPGA: Neural Parametric Gaussian Avatars – high-fidelity ... by throwaway1105q on Friday May 31, 2024 @06:50AM (#40533428)
Indeed. That's what I'm saying - you decide you want to research and so you publish. Nobody decides to publish and so does research.
[ Parent | on HN ]
Re:NPGA: Neural Parametric Gaussian Avatars – high-fidelity ... by BriggyDwiggs42 on Friday May 31, 2024 @09:51AM (#40535155)
How is this a useful critique? The publishing being a subgoal doesn’t mean it’s not still a goal.
[ Parent | on HN ]
Re:NPGA: Neural Parametric Gaussian Avatars – high-fidelity ... by throwaway1105q on Friday May 31, 2024 @02:14PM (#40538530)
How is that a useful critique? Yes, researchers publish research.
[ Parent | on HN ]
Re:NPGA: Neural Parametric Gaussian Avatars – high-fidelity ... by throwaway1105q on Friday May 31, 2024 @02:15AM (#40532026)
I don't understand your question. There are some cases of abuse and so the researchers shouldn't discuss applications of the research?
[ Parent | on HN ]