[HN Gopher] Vtracer: Next-Gen Raster-to-Vector Conversion
___________________________________________________________________
Vtracer: Next-Gen Raster-to-Vector Conversion
Author : s1291
Score : 120 points
Date : 2023-11-22 10:10 UTC (1 days ago)
(HTM) web link (github.com)
(TXT) w3m dump (github.com)
| rootlocus wrote:
| Maybe now Affinity Designer can introduce a tracing feature and
| further catch up to Adobe Illustrator.
| wiz21c wrote:
| and inkscape
| devit wrote:
| Maybe Facebook's Segment Anything could replace the first
| clustering step?
| spaceprison wrote:
| I had a similar idea the other day after fighting with inkscape
| tracing! The problem with auto tracing is lack of content
| awareness so it's just shapes and colors leading to strange
| objects that require lots of tinkering.
|
| I'm going to try it: Use segment anything to get object masks,
| Trace each object separately and combine from there!
| larodi wrote:
| It may be much slower, though segment-anything works quite
| okay from my tests. But still - great work, cant wait to use
| it in my next design. :D
| ttul wrote:
| This would make for a nice ComfyUI custom node.
| westurner wrote:
| > _Comparing to Potrace which only accept binarized inputs
| (Black & White pixmap), VTracer has an image processing
| pipeline which can handle colored high resolution scans.
| tl;dr: Potrace uses a O(n^2) fitting algorithm, whereas
| vtracer is entirely O(n)._
|
| What is the Big-O of the algorithm with Segment Anything or
| other segmentation approaches?
|
| Potrace: https://en.wikipedia.org/wiki/Potrace
|
| The Ctrl-L to _Simplify_ Inkscape feature attempts to
| describe the same path with fewer points /bezier curves.
|
| Could this approach also help with 3d digitization?
| raphlinus wrote:
| For the generation of simplified Bezier paths, I hope they
| consider the new methods in kurbo[1]. These have some fairly
| fancy math behind them and result in pretty close to a global
| optimum in terms of the minimal number of segments needed to hit
| an error target. They _don 't_ do implicit low-pass filtering,
| rather treat the input as a source of truth, but perhaps options
| could be added for that.
|
| [1]: https://docs.rs/kurbo/latest/kurbo/simplify/index.html
| Animats wrote:
| It doesn't seem to do all that well on blueprint type line
| art.[1] It seems to do a lot better when it has areas to
| separate. Which is not surprising, considering the approach.
|
| This is about as well as I was doing on scanned engineering
| drawings in 1983. I wrote Autodesk's CAD/Camera. 20 minutes of
| compute to process a drawing on an IBM PC/AT. You can be too
| early. By now, a product in that space should be recognizing not
| just lines, but dimensions, and generating a properly dimensioned
| CAD model.
|
| [1]
| https://github.com/visioncortex/vtracer/blob/master/docs/ima...
| ska wrote:
| > You can be too early.
|
| Yes, yes you can. I worked on a project than included hardware
| are related workflow for digitizing analog input to essentially
| a digital image processing workflow, just because the digital
| sensors weren't _quite_ there yet. A few years later, they
| were.
| andrewstuart wrote:
| This is the most impressive raster to vector I have seen:
|
| https://vectormagic.com
|
| Vtracer doesn't seem to do as well.
| icyfox wrote:
| This is the best I've found as well. They also have a new
| offering (different internal model, similar quality evidently)
| that I've used back when it was in a free unlimited trial. Not
| sure the status right now: https://vectorizer.ai/
| ChrisMarshallNY wrote:
| I use Adobe Illustrator for the fairly rare occasions that I
| need to do it.
|
| Since I already have it, and use it to generate almost all my
| graphic assets, it makes sense.
| solardev wrote:
| IME VectorMagic does a much better job on more complex
| drawings.
___________________________________________________________________
(page generated 2023-11-23 23:01 UTC)