AI Paper Atlas

Research map / 3D vision / Gaussian splatting

Dropping Anchor and Spherical Harmonics for Sparse-view Gaussian Splatting

Shuangkang Fang, I-Chao Shen, Xuanyang Zhang, Zesheng Wang, Yufeng Wang, Wenrui Ding, Gang YU, Takeo Igarashi

CVPR 2026 · 3D vision › Gaussian splatting · approach: Compact and efficient Gaussian splatting · 6 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add anchor-based dropout (ablation)3DGS (sparse view) · LLFF (3 views)PSNR: 19.17 -> 20.47Improved
add SH dropout on top of anchor dropout (ablation)DropAnSH-GS · LLFF (3 views)PSNR: 20.47 -> 20.68Improved
add SH dropout alone (ablation)3DGS (sparse view) · LLFF (3 views)SSIM: 0.646 -> 0.641No clear effect
drop SH by degree instead of randomly (ablation)DropAnSH-GS · Blender (8 views)PSNR: 25.12 -> 25.50Improved
replace independent Gaussian dropout with anchor dropout plus SH dropoutDropGaussian · LLFF (3 views)PSNR: 20.33 -> 20.68Improved
truncate to SH0 at inference (ablation)DropAnSH-GS · MipNeRF-360 (12 views)PSNR: 18.58 (3DGS) -> 19.71; size 143.4 -> 33.8 MBImproved
truncate SH3 to SH2 at inference (ablation)DropAnSH-GS · MipNeRF-360 (12 views)PSNR: 19.93 -> 19.95; size 122.6 -> 81.1 MBMixed
plug DropAnSH-GS into Scaffold-GSScaffold-GS · LLFF (3 views)PSNR: 18.62 -> 19.84Improved
plug DropAnSH-GS into CoR-GSCoR-GS · LLFF (3 views)LPIPS: 0.202 -> 0.203No clear effect
raise anchor sampling rate from 0.02 to 0.04 (ablation)DropAnSH-GS · LLFF (3 views)PSNR: 20.68 -> 19.97Hurt
use 1 neighbor instead of 10 (ablation)DropAnSH-GS · LLFF (3 views)PSNR: 20.68 -> 20.12Hurt
add anchor and SH dropout to 3DGS: training time3DGS · LLFF (3 views)Training time: 741.6s -> 760.2sNo clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy