https://hackerpaper.kaipfister.de/p/2309.12302/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMThttps://news.ycombinator.com/item?id=38409292urn:hackerpapers:mention:2309.12302:38409292Fri, 24 Nov 2023 22:55:45 GMT<p>Yeah unfortunately differentiable SVG rendering is still something that is very difficult to accomplish with diffusion models. I looked into this last year and found VectorFusion [0][1], which appears to be using a similar technique to this app - generate the raster image and then apply a vectorization tracer. This leads to the blobbiness you see, given the way the diffusion model generates the image and the tracer applies to the output. There have been a few attempts (i.e. this recent one [2][3]) to attempt to fine-tune the parameters of the SVG with image segmentation, before comparing…</p><p><a href="https://hackerpaper.kaipfister.de/p/2309.12302/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CV