From: Whisky-dave <whisky.dave@gmail.com>
Subject: Re: On "real" photography vs collage
Full headers:
X-Received: by 10.55.221.196 with SMTP id u65mr4058116qku.18.1509545184883;
Wed, 01 Nov 2017 07:06:24 -0700 (PDT)
X-Received: by 10.31.153.21 with SMTP id b21mr459676vke.13.1509545184696; Wed,
01 Nov 2017 07:06:24 -0700 (PDT)
Path: news.netfront.net!goblin3!goblin.stu.neva.ru!news.misty.com!border2.nntp.dca1.giganews.com!nntp.giganews.com!k31no190165qta.1!news-out.google.com!v14ni371qtc.0!nntp.google.com!k31no190163qta.1!postnews.google.com!glegroupsg2000goo.googlegroups.com!not-for-mail
Newsgroups: rec.photo.digital
Date: Wed, 1 Nov 2017 07:06:24 -0700 (PDT)
In-Reply-To: <otcj1m$1160$1@gioia.aioe.org>
Complaints-To: groups-abuse@google.com
Injection-Info: glegroupsg2000goo.googlegroups.com; posting-host=138.37.90.65; posting-account=Fal3rgoAAABua4brvRuRwdmPfigIDi6x
NNTP-Posting-Host: 138.37.90.65
References: <otcj1m$1160$1@gioia.aioe.org>
User-Agent: G2/1.0
MIME-Version: 1.0
Message-ID: <9bf5dd1a-5da9-417a-8fb0-a9b5d543e180@googlegroups.com>
Subject: Re: On "real" photography vs collage
From: Whisky-dave <whisky.dave@gmail.com>
Injection-Date: Wed, 01 Nov 2017 14:06:24 +0000
Content-Type: text/plain; charset="UTF-8"
Lines: 30
Print Article
Forward Article
On Wednesday, 1 November 2017 13:43:23 UTC, Mayayana  wrote:
> Interesting development apropos of last week's discussion:
> 
>
https://hothardware.com/news/nvidia-neural-network-generates-photore...
> 
>   I can't say that I really understand this technology,
> but it apparently uses something like an internal
> software argument to systematically improve on a
> result. what they've done is to generate realistic
> faces from limited data. I could imagine this being
> used for image improvement. Example: Feed a bad
> photo into a program and then give it good photos
> of the people in photo #1, with the result being
> a "clean-up" of those faces.
>   The result would be something like a "realistic
> fabrication", just as these sample faces are.
> 
>  They all look convincing to me, except for the
> second image in from the top left and the second
> one down from the top left, which both look
> like cross-dressers. 

cross-dressers do exist and not everyone looks or is either 100% male or 100% female.

>I find it intriguing that the
> software seems to be able to put a soul behind
> the eyes, so to speak, but has trouble with the
> subtleties of gender features.

I don't see it that way, but what interests me more is where these are photographs and could they be
entered into say a portait section of a photogrphy competition as they are about as real as my
favourite warbird.  (Romulan)