Dropping Anchor and Spherical Harmonics for Sparse-view Gaussian Splatting · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2602.20933/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTDropping Anchor and Spherical Harmonics for Sparse-view Gaussian Splatting — mentioned by deckar01https://news.ycombinator.com/item?id=48165077urn:hackerpapers:mention:2602.20933:48165077Sun, 17 May 2026 00:36:09 GMT<p>After seeing the fixed 3rd order spherical harmonics I was curious how that might be optimized. DropAnSH-GS (Feb 2026) drops out high order SH coefficients to force low frequency color into low order coefficients (3.4. Spherical Harmonics Dropout). They conclude that high order coefficients can be discarded to trade off speed/size for detail. They don’t seem to have considered encoding as sparse coefficients post training to discard all near zero coefficients. https://arxiv.org/pdf/2602.20933</p><p><a href="https://hackerpaper.kaipfister.de/p/2602.20933/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CV