mlsanityData to 7 Oct 2026

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

arXiv 2610.09343 ↗First posted 7 Oct 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

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× at standard resolution and 1.238× at 3840 pixels wide, with -0.007/-0.023 dB mean PSNR change. Six integrations with existing opacity-aware bounds yield 1.009×--1.121× compiler-only speedups. For four ports from 3σ 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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). First posted on arXiv 7 Oct 2026.

Builds on

No reference list yet.

Built on by

Not cited yet.