https://hackerpaper.kaipfister.de/p/1905.09304/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMThttps://news.ycombinator.com/item?id=20491369urn:hackerpapers:mention:1905.09304:20491369Sun, 21 Jul 2019 14:07:14 GMT<p>The main objection I have is that a differentiable renderer is giving you the rope to hang yourself, it helps you work in the wrong space. There is some special structure to the rendering problem, that is probably tackled better. One inherent difficulty for efficient solving is working with multiple hypothesis at the same time (which differentiable renderer makes you miss). Also there is some special structure of the probability space which is &quot;once you know the position of the camera it is easy to render, once you know the position of the objects it is easy to locate the camera&quot;. This means…</p><p><a href="https://hackerpaper.kaipfister.de/p/1905.09304/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CV