----------------------------------------------------------------------------------
@MSGID: <CbadnY3FCtijjZj4nZ2dnZfqn_udnZ2d@giganews.com>
887c2ef0
@REPLY: <150920231023310505%nospam@nospam.invalid>
84155a3b
@REPLYADDR geoff <geoff@nospamgeoffwood.org>
@REPLYTO 2:5075/128 geoff
@CHRS: CP866 2
@RFC: 1 0
@RFC-References:
<Pine.NEB.4.64.2309142230540.5510@panix3.panix.com> <d5a5e815-3078-4000-90b1-58b2a2635ea3n@googlegroups.com>
1@reader2.panix.com> <150920231023310505%nospam@nospam.invalid>
@RFC-Message-ID:
<CbadnY3FCtijjZj4nZ2dnZfqn_udnZ2d@giganews.com>
@TZUTC: 1200
@PID: Mozilla/5.0 (Windows NT 10.0; Win64; x64;
rv:102.0) Gecko/20100101 Thunderbird/102.15.0
@TID: FIDOGATE-5.12-ge4e8b94
On 16/09/2023 2:23 am, nospam wrote:
> In article
1@reader2.panix.com>, danny burstein
> <dannyb@panix.com> wrote:
>
>>> It did make me wonder how or if AI could be used to simulate such a thing,
>>> but not sure how it could be done
>>> for reducing reflections.
>>
>> I can see (IswIdt) some ways in which image processing
>> of multiple, slightly different angle photos, could
>> be combined in sugh a way as to "figure out" what parts
>> of each image are "glare" and eliminate them. But I`m
>> not aware of any system available to The Great Unwashed
>> handles that.
>
> maybe not glare (yet), but ai is here.
>
> <https://www.engadget.com/samsung-explains-its-fake-moon-photos-17023389
> 6.html>
> Samsung is hoping to talk its way out of a controversy over its
> camera processing technology. The company has shared an explanation
> of the Moon photo detection system it has used since the Galaxy S21.
> If you have Scene Optimizer turned on, AI detects when you`re taking
> a clear photo of the Moon at 25X zoom or above. The tech lowers the
> brightness, captures multiple frames (to produce a bright, low-noise
> picture) and uses a neural network to enhance the detail using a
> high-resolution reference image for comparison.
Yeah, but what about NASA ...
geoff
--- Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:102.0) Gecko/20100101
Thunderbird/102.15.0
* Origin: Dis (2:5075/128)
SEEN-BY: 5001/100 5005/49 5015/255 5019/40 5020/715
848 1042 4441 12000
SEEN-BY: 5030/49 1081 5058/104 5075/128
@PATH: 5075/128 5020/1042 4441