AI Paper Atlas

Research map / 3D vision / Gaussian splatting

Fast and Compact 3D Gaussian Splatting with Polarized Opacity Prior

Zi-Ming Wang, Kevin Duan, Ko Wei Huang, Akihiro Sugimoto, Shang-Hong Lai

ECCV 2026 · 3D vision › Gaussian splatting · approach: Regularization and primitive design for 3DGS · 0 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 Polarized Opacity Prior (POP) instead of opacity reset (ablation)gsplat-based 3DGS with L2 and blur densification · Mip-NeRF 360number of Gaussians: 548k -> 268kImproved
add POP instead of opacity reset (ablation)gsplat-based 3DGS · Tanks & TemplesPSNR: 22.91 -> 23.62Improved
add POP instead of opacity reset (SSIM and LPIPS) (ablation)gsplat-based 3DGS · Mip-NeRF 360LPIPS: 0.260 -> 0.277Hurt
add POP on top of L2 + blur densification (ablation)gsplat-based 3DGS · Mip-NeRF 360number of Gaussians: 583k -> 268k; PSNR 27.22 -> 27.01Mixed
add blur-based densification to L2 loss (ablation)gsplat-based 3DGS · Mip-NeRF 360PSNR: 26.57 -> 27.22Improved
replace L1 with L2 loss (ablation)3DGS training · Mip-NeRF 360PSNR at comparable Gaussian countImproved
extend blur densification to 3k-15k (ablation)Ours · Mip-NeRF 360, Tanks & Temples, Deep BlendingPSNR: +0.16 on Mip-NeRF 360, -0.07 on T&T, -0.37 on DBMixed
halt blur densification early (3k-4k) (ablation)Ours · Mip-NeRF 360PSNR: 27.01 -> 26.54Hurt
compact training vs original 3DGSOurs · Mip-NeRF 360training time (s): 1,304 -> 279Improved
compact training vs original 3DGSOurs · Deep BlendingPSNR: 29.847 -> 28.626Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 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