PrimeDepth: Efficient Monocular Depth Estimation with a Stable Diffusion Preimage · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2409.09144/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTPrimeDepth: Efficient Monocular Depth Estimation with a Stable Diffusion Preimage — mentioned by in-silicohttps://news.ycombinator.com/item?id=46831775urn:hackerpapers:mention:2409.09144:46831775Sat, 31 Jan 2026 00:11:21 GMT<p>Yes, it reproduces what it is given by modelling the rules of physics, geometry, etc. For example, image generators like stable diffusion carry strong representations of depth and geometry, such that performant depth estimation models can be built out of them with minimal retraining. This continues to be true for video generation models. Early work on the subject: https://arxiv.org/pdf/2409.09144</p><p><a href="https://hackerpaper.kaipfister.de/p/2409.09144/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CV