AI Paper Atlas

Research map / 3D vision / Gaussian splatting

Confidence-Based Mesh Extraction from 3D Gaussians

Lukas Radl, Felix Windisch, Andreas Kurz, Thomas Köhler, Michael Steiner, Markus Steinberger

ECCV 2026 · 3D vision › Gaussian splatting · approach: Regularization and primitive design for 3DGS · 1 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 improved decoupled appearance embedding to SOF (ablation)SOF · Tanks & TemplesF1: 0.474 -> 0.493Improved
add confidence-weighted photometric loss L_conf (ablation)SOF + improved appearance · ScanNet++F1: 0.625 -> 0.655Improved
add per-primitive color variance loss (ablation)SOF + appearance + L_conf · Tanks & TemplesF1: 0.509 -> 0.519Improved
add per-primitive normal variance loss (ablation)SOF + appearance + L_conf + color-var · ScanNet++F1: 0.658 -> 0.668Improved
add normal variance loss (ablation)SOF + appearance + L_conf + color-var · Tanks & TemplesF1: 0.519 -> 0.521Improved
use appearance-corrected image only in the luminance term of D-SSIM (decoupling) (ablation)improved appearance module · Tanks & TemplesF1: 0.490 -> 0.493Improved
drop the luminance term from D-SSIM instead of compensating it (ablation)improved appearance module · Tanks & TemplesF1: 0.493 -> 0.483Hurt
architectural improvements to VastGaussian appearance (exp activation, padding, positional encoding) (ablation)VastGaussian appearance · Tanks & TemplesF1: 0.475 -> 0.484Improved
add confidence-steered densification (ablation)Ours · Tanks & TemplesF1 and Gaussian count: F1 0.516 -> 0.521; 1.53M -> 1.27M GaussiansImproved
enable L_conf later in training (iteration 15K instead of 500) (ablation)Ours · Tanks & TemplesF1: 0.521 -> 0.501Hurt
enable L_conf at iteration 5K instead of 500 (ablation)Ours · Tanks & TemplesF1: 0.521 -> 0.517Hurt
increase normal variance weight tenfold (0.005 to 0.05) (ablation)Ours · Tanks & TemplesF1: 0.521 -> 0.515Hurt

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