[HN Gopher] The Night Watch: The Missing Pieces
       ___________________________________________________________________
        
       The Night Watch: The Missing Pieces
        
       Author : BjoernKW
       Score  : 151 points
       Date   : 2021-06-24 09:33 UTC (13 hours ago)
        
 (HTM) web link (www.rijksmuseum.nl)
 (TXT) w3m dump (www.rijksmuseum.nl)
        
       | Daub wrote:
       | Art teacher speaking. Cropping is surprisingly easily to detect
       | in an aesthetic image. Its kind of like reading a half-finished
       | book. Aesthetic images are designed for an defined format. If
       | that format is changed nearing completion, the geometry feels
       | wrong. It is even easier in paintings, where there are overt
       | brush marks. The structure of a brush mark is strongly framed by
       | the format of the canvas.
       | 
       | Anyone interested in the recreation of famous incomplete
       | paintings, should check out Manet's The Execution of Emperor
       | Maximilian. This is a painting Manet gave up on, and chopped up
       | into smaller studies.
       | 
       | https://www.nationalgallery.org.uk/media/33986/n-3294-00-000...
       | 
       | There are sketches that indicate the format he was aiming for,
       | but Manet was a famous experimenter, so we will probably never
       | know.
        
       | bruce343434 wrote:
       | I was hoping for a before/after comparison picture, but I can't
       | find it.
        
       | appleflaxen wrote:
       | For anyone else who wants context before watching:
       | 
       | this is about the use of AI to reconstruct missing pieces of a
       | Rembrandt painting ("Night Watch") using a contemporaneous copy
       | from Lundens. After the Lundens painting was made, the Rembrandt
       | original was cropped aggressively (~30 cm on a side) in order to
       | fit onto a particular wall where it hung.
       | 
       | Now that it is considered a masterpiece, they are trying to
       | computationally estimate what those cropped sections looked like
       | using Lunden's copy.
        
       | DFHippie wrote:
       | A vaguely similar anecdote:
       | 
       | My grandfather, a taciturn, unsentimental Quaker mechanical
       | engineer, was given the job of preparing a Methodist church to be
       | a Quaker meetinghouse. The church had tall stained glass windows,
       | but Quaker meetings are un- or minimally adorned. Well, Dan was a
       | competent, efficient fellow. In short order the meeting was fit
       | for occupancy again. The stained glass windows were gone except
       | for a rose window. Some time after some of the Methodists came by
       | asking what had become of the tall stained glass windows. They
       | were memorial windows and they wanted to keep them as memorials.
       | No one knew. Questions went around. Eventually someone asked Dan.
       | He said they were under the gravel in the parking lot. What! Why
       | are they there!? He just said, "they were ugly."
       | 
       | I hope the spare pieces of the Night Watch weren't ugly, and if
       | they were, the job of fitting them to the space wasn't given to
       | some 18th century Dan.
        
         | hutzlibu wrote:
         | Or the elderly women, who "restored" a historical painting.
         | 
         | https://en.wikipedia.org/wiki/Ecce_Homo_(Mart%C3%ADnez_and_G...
        
         | MomoXenosaga wrote:
         | It is entirely possible that at the time the Nightwatch was
         | considered ugly. Let us not forget Rembrandt died an
         | impoverished man.
         | 
         | How art is appreciated changes with the times.
        
           | coyotespike wrote:
           | To be fair, Rembrandt was famous and very well-employed in
           | his own day, he just spent money like it was going out of
           | style. Had he saved a little he'd have died rich.
        
       | stefanpie wrote:
       | Robert Erdmann also gave a keynote talk at PyCon US 2021 about
       | how they used Python for most of digitization and processing of
       | the Night Watch (aka Operation Night Watch). Fascinating talk
       | with tones of technical details.
       | 
       | Link:
       | https://www.youtube.com/watch?v=z_hm5oX7ZlE&list=PL2Uw4_HvXq...
        
       | ElViajero wrote:
       | This is a cool project. The part that I am not so sure about is
       | why don't they just use an artist to paint the missing part? What
       | is the advantage of using an AI?
       | 
       | My guess, even that I hope not, is that people thinks that AI is
       | going to be more impartial, more accurate, less biased. The
       | reality is that an AI, as used in this example, is going to be
       | over-fitting.
       | 
       | An artist can understand Lunden and Rembrant art and use that
       | knowledge to produce something closer to the intention of the
       | artist and the copy.
       | 
       | Cool project, but a dangerous precedent if people thinks that AI
       | provides unbiased reality, that using AI you can show "how it
       | really looked" as something more accurate that any human con
       | achieve. Constructing something from missing data is always
       | guesswork, whenever the intelligence is natural or artificial.
        
         | treve wrote:
         | They mention in the video that they could ask a person to make
         | the changes with Photoshop, but the reason they give is: "Then
         | it would be that artist's work, not Rembrandt".
         | 
         | That statement rubs me the wrong way a bit though, because
         | whether you ask a person or a computer model to copy
         | Rembrandt's style, in each case it's still a copy, and I would
         | argue in each case there's still a(n) artist(s) mimicking
         | Rembrandt, just using different tools.
         | 
         | > My guess, even that I hope not, is that people thinks that AI
         | is going to be more impartial, more accurate, less biased. The
         | reality is that an AI, as used in this example, is going to be
         | over-fitting. > Cool project, but a dangerous precedent if
         | people thinks that AI provides unbiased reality, that using AI
         | you can show "how it really looked" as something more accurate
         | that any human con achieve. Constructing something from missing
         | data is always guesswork, whenever the intelligence is natural
         | or artificial.
         | 
         | I think this is an excellent take.
        
         | floatrock wrote:
         | I'm not gonna anthropomorphize the AI and say "the AI is the
         | artist", but the AI is definitely an art _style_.
         | 
         | I see it as just an old-meets-new mashup, craftfully executed.
         | Any artist/technique you use isn't going to be the original
         | Rembrant, so the choice of what artist/technique you use is
         | just a question of aesthetics and taste.
         | 
         | Here we're just exploring a new technique of the 21st century.
        
       | ffhhj wrote:
       | Let's make those paintings Ships of Theseus: recreate the missing
       | parts around the paintings up to universe scale.
        
       | shadeslayer_ wrote:
       | Anyone else thought this was about the Night's Watch in the Game
       | of Thrones books/novels?
       | 
       | I'll see myself out..
        
         | astrange wrote:
         | Could've at least thought it was about a Dutch translation of
         | the Terry Pratchett book.
        
       | defaultname wrote:
       | Very interesting watch.
       | 
       | What sort of NN would be used to warp two compositionally similar
       | images to match each other in structure? In the example the copy
       | painting had almost all of the same general components, laid out
       | with fairly significant differences, and they warped it to match
       | quite precisely.
        
         | danbruc wrote:
         | Without a neural network one would probably use optical flow
         | [1] and I guess you could train a neural network to predict
         | optical flow and then use that flow to align the two inputs. I
         | have no answer to your specific question, what kind of neural
         | network architecture would be best suited but given the task it
         | seems reasonable to assume some form of convolutional neural
         | network.
         | 
         | [1] https://en.wikipedia.org/wiki/Optical_flow
        
         | jvanderbot wrote:
         | I'm taking your question without context, so sorry if it
         | doesn't make sense: Warping images to match based on structure
         | / features is common in much of image processing and _requires_
         | no NN since we know how to do it. (But may be enhanced by NN).
         | 
         | The basic idea is:
         | 
         | 1. Find features in images A and B (SURF / SIFT are common).
         | However, maybe a NN could find interesting features here?
         | 
         | 2. Match features so you know what feature from A is where in
         | B. Again, a NN could potentially do this "better".
         | 
         | 3. Compute a homography (translation between planes of
         | features) or procrustes transform (or other types of
         | transformations)
         | 
         | 4. For each pixel (p) in the target frame (B), take the inverse
         | of the transformation to find the pixel of the original frame
         | (A) (which is usually a fractional pixel because it won't line
         | up)
         | 
         | 5. interpolate between nearby pixels in (A) to get the "true"
         | pixel value at (p) in (B). Perhaps a NN could improve this
         | interpolation? We've seen this in super resolution, for
         | example.
         | 
         | You can easily reproduce these steps with just a few function
         | calls in OpenCV. Try it out. https://opencv.org/
         | 
         | Up to step 3 is very helpful to answer questions like: "How
         | much did the camera move between captures of image A and B. So
         | now you can solve structure from motion, visual odometry, etc.
         | This is typically how quadrotors navigate with cameras.
        
           | danbruc wrote:
           | Would SIFT or SURF features actually work in this scenario,
           | that was also one of my thoughts, but then I considered that
           | the inputs are not photographs of the same objects from
           | different angles but a painting and a manual reproduction of
           | it. I would be really interested in knowing whether those
           | features are robust enough under the distortions in such a
           | scenario. And how far could one push this, could you still
           | align the Mona Lisa with a good pencil drawing of it?
        
             | jvanderbot wrote:
             | I have no idea! Careful feature selection is very
             | important. If you only have edge information, then
             | extracting edges in both images seems like a reasonable
             | pre-processing step.
        
       | dominicjj wrote:
       | That is brilliant. I saw the Night Watch at the end of a busy day
       | and it was pretty much the only thing I had time for in the Rijks
       | Museum. I will have to return to Amsterdam and see the expanded
       | version.
        
         | BrandoElFollito wrote:
         | The first time I went to the Rijks Museum I almost missed it.
         | 
         | I saw on the left side of the main gallery (this is from
         | memory, 30 years back) a small painting (say, 40x20 cm) which
         | had a name similar (or the same) as The Night Watch and I
         | thought that it is a great deal for such a nice but average
         | painting.
         | 
         | Then I saw some people standing in the middle of the gallery
         | watching something and I discovered the painting :)
        
           | BjoernKW wrote:
           | The impact also depends on the direction from which one
           | approaches the painting.
           | 
           | If you enter from the room to the right hand side of the
           | Night Watch it's almost easy to miss, not least because the
           | ship models in the rooms that precede it are quite
           | impressive, too.
           | 
           | From the Great Hall and the Eregalerij (Gallery of Honour)
           | the effect is positively awe-inspiring. I've once heard
           | someone describe the Rijksmuseum as a cathedral of
           | Enlightenment. The Night Watch is the centrepiece that
           | cathedral was built around.
        
       ___________________________________________________________________
       (page generated 2021-06-24 23:01 UTC)