https://hackerpaper.kaipfister.de/p/1901.05103/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMThttps://news.ycombinator.com/item?id=25952638urn:hackerpapers:mention:1901.05103:25952638Fri, 29 Jan 2021 01:58:25 GMT<p>My understanding of this paper (please comment/correct based on your understanding): * Instead of using a single latent feature per each implicit surface, the authors propose using a &quot;volume&quot; of latent features per each surface. This allows for the NNs to better capture the geometric detail while remaining relatively shallow. The result is a more accurate and faster to compute neural SDF. Contrary to the claim of another comment, the neural SDF alone is not the interesting part of this paper--the prior works points to at least three other papers that have explored the idea of representing an…</p><p><a href="https://hackerpaper.kaipfister.de/p/1901.05103/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CVhttps://news.ycombinator.com/item?id=18977113urn:hackerpapers:submission:1901.05103:18977113Wed, 23 Jan 2019 10:23:00 GMT<p>DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation</p><p></p><p>2 points; 0 discussion replies on HN. <a href="https://hackerpaper.kaipfister.de/p/1901.05103/">Paper and source history</a>. A submission is not an endorsement.</p>cs.CV