SyncAI.news, a Varaisys broadcasting
TileSkipper: Region-Adaptive Tile Pruning for 3D Gaussian Splatting
JL

Jingxing Li, Yongjae Lee, Deliang Fan, Abhay Kumar Yadav, Cheng Peng, Rama Chellappa

· 1 min read

ResearcharXiv cs.CV

TileSkipper: Region-Adaptive Tile Pruning for 3D Gaussian Splatting

arXiv:2610.09343v1 Announce Type: new Abstract: Tiled 3D Gaussian Splatting rasterizers often use one scene-wide contribution cutoff for tile enumeration, although content differs in its sensitivity to support truncation. TileSkipper selects a static per-Gaussian cutoff policy for a frozen checkpoint. Calibration renders measure candidate pair savings and an isolated-removal distortion proxy that accounts for front transmittance and background color. The method allocates cutoffs across 64 Gaussian groups and accepts policies only after complete renders on disjoint selection views. The exported policy uses one byte per Gaussian, with no parameter updates, additional kernel, or per-frame policy inference. Across 13 scenes from Mip-NeRF 360, Tanks & Temples, and Deep Blending, a fixed-policy AccuTile sweep gives dataset-macro speedups of $1.088\times$ at standard resolution and $1.238\times$ at 3840 pixels wide, with $-0.007/-0.023$ dB mean PSNR change. Six integrations with existing opacity-aware bounds yield $1.009\times$--$1.121\times$ compiler-only speedups. For four ports from $3\sigma$ rasterizers, we separately attribute the prior exact-bound transition and our incremental gain. Matched-quality ablations show modest gains over scene-global calibration and parity with per-Gaussian control; the standalone comparison with AdaGScale is regime-dependent.

Original source

This story was published by arXiv cs.CV and written by Jingxing Li, Yongjae Lee, Deliang Fan, Abhay Kumar Yadav, Cheng Peng, Rama Chellappa. SyncAI.news shows a preview; the complete article is on the publisher's site.

Read the full story on arxiv.org

Similar News