[HN Gopher] The Klimt Color Enigma
       ___________________________________________________________________
        
       The Klimt Color Enigma
        
       Author : emilwallner
       Score  : 62 points
       Date   : 2021-10-22 10:50 UTC (1 days ago)
        
 (HTM) web link (artsandculture.google.com)
 (TXT) w3m dump (artsandculture.google.com)
        
       | woodruffw wrote:
       | Normally I roll my eyes at these kinds of ML applications (I've
       | seen a lot of haphazard applications of upscaling and auto-
       | colorization to archival footage, resulting in really garish and
       | unrealistic transformations), but this effort appears to have
       | been thoughtfully performed (with references to Klimt's
       | contemporaneous works and living experts).
        
       | tartoran wrote:
       | Mistery is like a magnet for the imagination. I personally like
       | when a piece of the puzzle is missing: it makes us think.
        
       | mechanical_bear wrote:
       | Quick!!! We need some good PR! Push the Klimt story!
        
       | kwelstr wrote:
       | Great work, I greatly admire Klimt's art and these paintings were
       | such an important part of his artistic development and so sad
       | they were destroyed on purpose so the other side wouldn't have
       | them.
       | 
       | That website is a pain to read on a desktop computer thou...
       | maybe ok on mobile?
        
         | jbaber wrote:
         | I'm a big Klimt fan and am very impressed with this (especially
         | Jurisprudence). I was thinking, though: "this is so hard to see
         | on mobile. Maybe better on desktop."
        
           | ambyra wrote:
           | I can confirm it is terrible on both. What a great article
           | though.
        
       | egypturnash wrote:
       | When I skipped down to the bottom of this page to look at the
       | actual art under discussion, it gave me a popup that told me I
       | had earnt a fucking _badge_ for reading this page all the way
       | through.
       | 
       | I hate this fucking future.
        
       | Palomides wrote:
       | does anyone else feel this is disrespectful to artists? having a
       | computer make up colors to apply to art? it's completely devoid
       | of the human intent that chose the original colors
        
         | alisonkisk wrote:
         | Klimt is dead, and the originals are missing.
        
         | Daub wrote:
         | Not exactly made up. Having only the lightness values to start
         | with, The task is to define the hue and saturation. Though in
         | theory there is no way to know for certain what they originally
         | were, in practice certain lightness values are associated with
         | some hues more than others. Also, saturation values tend to
         | follow lightness values quite closely. Add to that the fact
         | that Klimt (like most painters) employed a habitual pallet, you
         | are half was to a good guess.
        
         | woodruffw wrote:
         | I empathize with this position, but I think this situation is
         | closer to authentic restoration (which the art world is okay
         | with, generally speaking) than an unguided machine
         | transformation of a human work.
         | 
         | (I've visited just about every Klimt exhibit in Vienna,
         | including the one that these B&W photographs are in. I think
         | they've done a remarkably faithful job here, down to accurately
         | capturing the subperiod of Klimt's "gold period").
        
         | aeturnum wrote:
         | No, absolutely not.
         | 
         | I think that one has to be careful with _labeling_ - these
         | works are highly researched guesses based on lots of sources
         | but are not  "the article itself." But I think this process,
         | where they are trying to be a thorough as possible in guessing
         | what colors Klimt might have used mechanistically, is much more
         | respectful than other techniques. Consider the recent Vermeer
         | restoration[1] (hn discussion at [2]): 'restoring' the painting
         | in this way alters the actual article and could be altering the
         | intent of the artist. I support the work, but I think there's a
         | basic element of uncertainty to it.
         | 
         | At the end of the day, if you don't want to accept the
         | machine's guess at the colors Klimt used, you don't need to!
         | You have access to the same archival documentation of what his
         | lost paintings looked like as everyone else.
         | 
         | [1] https://hyperallergic.com/672345/vermeer-restoration-
         | finally...
         | 
         | [2] https://news.ycombinator.com/item?id=28468802
        
         | hairofadog wrote:
         | Speaking only for myself, no! It's just borrowing and playing
         | with ideas, which artists do all the time. (I have an education
         | in fine arts, for whatever it's worth [0])
         | 
         | [0]: nothing, both literally and figuratively
        
           | Palomides wrote:
           | I'm fine with playing with ideas, but the fact that it's
           | google smacks of "look, the computer can replicate/replace
           | the human", which has a very different vibe than, say, Dali
           | coloring Goya
        
             | hairofadog wrote:
             | Yep, good point.
        
             | mechanical_bear wrote:
             | The timing, considering it was posted by someone connected
             | to Google and in light of recent news, seems suspect.
        
         | canjobear wrote:
         | They have human Klimt experts helping too.
        
         | googlryas wrote:
         | It seems different when we're just trying to guess what the
         | actual colors were, since the artist is dead and the painting
         | is destroyed, and we only have a black and white copy + textual
         | description of the painting.
        
       | tudorw wrote:
       | "The algorithm is trained on 91749 artworks from Google Arts &
       | Culture"
       | 
       | I'd like to have a play with that, is it open or available?
        
         | emilwallner wrote:
         | Unfortunately not, but here are a few great public art
         | datasets: https://www.artnome.com/art-data. Rijksmuseum and
         | wikiart also have available datasets.
        
       | emilwallner wrote:
       | Thanks for the appreciation! I made the machine learning model
       | and wrote the article, happy to answer any questions.
       | 
       | Here's more information:
       | 
       | - 3D Gallery:
       | https://artsandculture.google.com/pocketgallery/kAUxTZBD8McZ...
       | 
       | - Video overview: https://www.youtube.com/watch?v=1xYpIM_BVTI
       | 
       | - This work will be part of an exhibition at the Museum of Rome
       | starting from 27th Oct, where you can also see Klimt's 'Portrait
       | of a Lady' that was missing for almost 23 years
       | 
       | - More Klimt artworks and articles:
       | https://artsandculture.google.com/project/klimt-vs-klimt
        
         | boulos wrote:
         | Awesome work! Btw, you could have also submitted this as Show
         | HN :).
        
         | CamperBob2 wrote:
         | Is there anywhere the actual restored artworks in the article
         | can be seen without having to navigate a lot of Web 3.0
         | gimmickry, or without having to scale up some 2000-era images
         | the size of postage stamps?
        
           | emilwallner wrote:
           | - Jurisprudence:
           | https://artsandculture.google.com/asset/jurisprudence-
           | recolo...
           | 
           | - Philosophy:
           | https://artsandculture.google.com/asset/philosophy-
           | recolored...
           | 
           | - Medicine: https://artsandculture.google.com/asset/medicine-
           | recolored-w...
        
             | CamperBob2 wrote:
             | I'll repeat my question.
             | 
             | https://i.imgur.com/TQIqFmb.png
        
         | zvr wrote:
         | Amazing work! Congratulations!
        
       ___________________________________________________________________
       (page generated 2021-10-23 23:01 UTC)