3D-free meets 3D priors: Novel View Synthesis from a Single Image with Pretrained Diffusion Guidance · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2408.06157/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMT3D-free meets 3D priors: Novel View Synthesis from a Single Image with Pretrained Diffusion Guidance — mentioned by axoltlhttps://news.ycombinator.com/item?id=41246292urn:hackerpapers:mention:2408.06157:41246292Wed, 14 Aug 2024 14:10:53 GMT<p>You are correct. I was confusing this technique with Novel View Synthesis through diffusion (recent paper: https://arxiv.org/abs/2408.06157) where inference means generating frames rather than points.</p><p><a href="https://hackerpaper.kaipfister.de/p/2408.06157/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CV