https://hackerpaper.kaipfister.de/p/2608.26948/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMThttps://news.ycombinator.com/item?id=50282103urn:hackerpapers:mention:2608.26948:50282103Wed, 28 Oct 2026 22:54:23 GMT<p>Hey Donovan, keep up the great work :) That reminds we, we had really weird results with splat-transform .sog output, when measuring the references for KISS-GS a couple months back. Why is the .sog curve dipping in quality when adding more primitives? It&#x27;s the &quot;POPSpa + .sog&quot; curve here, in the first Figure: https://arxiv.org/html/2608.26948v1 Always wanted to go back and measure with the latest splat-transform and find whats going on there.</p><p><a href="https://hackerpaper.kaipfister.de/p/2608.26948/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CV